bot: update RSS feed
This commit is contained in:
github-actions[bot]
438
feed.xml
438
feed.xml
@@ -7,349 +7,251 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Wed, 22 Apr 2026 00:08:55 +0000</lastBuildDate>
|
<lastBuildDate>Thu, 23 Apr 2026 00:13:48 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Significance and Stability Analysis of Gene-Environment Interaction using RGxEStat</title>
|
<title>SPRITE: From Static Mockups to Engine-Ready Game UI</title>
|
||||||
<link>https://arxiv.org/abs/2604.03337</link>
|
<link>https://arxiv.org/abs/2604.18591</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.03337.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meng'en Qin, Zhe Li, Xiaohui Yang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Genotype-by-Environment (GxE) interactions influence the performance of genotypes across diverse environments, reducing the predictability of phenotypes in target environments. In-depth analysis of GxE interactions facilitates the identification of how genetic advantages or defects are expressed or suppressed under specific environmental conditions, thereby enabling genetic selection and enhancing breeding practices. This paper introduces two key models for GxE interaction research. Specifically, it includes significance analysis based on the mixed effect model to determine whether genes or GxE interactions significantly affect phenotypic traits; stability analysis, which further investigates the interactive relationships between genes and environments, as well as the relative superiority or inferiority of genotypes across environments. Additionally, this paper presents RGxEStat, a lightweight interactive tool, which is developed by the authors and integrates the construction, solution, and visualization of the aforementioned models. Designed to eliminate the need for breeders and agronomists to learn complex SAS or R programming, RGxEStat provides a user-friendly interface for streamlined breeding data analysis, significantly accelerating research cycles. Codes and datasets are available at https://github.com/mason-ching/RGxEStat.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunshu Bai, RuiHao Li, Hao Zhang, Chien Her Lim, Ming Yan, Mengtian Li</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Game UI implementation requires translating stylized mockups into interactive engine entities. However, current "Screenshot-to-Code" tools often struggle with the irregular geometries and deep visual hierarchies typical of game interfaces. To bridge this gap, we introduce SPRITE, a pipeline that transforms static screenshots into editable engine assets. By integrating Vision-Language Models (VLMs) with a structured YAML intermediate representation, SPRITE explicitly captures complex container relationships and non-rectangular layouts. We evaluated SPRITE against a curated Game UI benchmark and conducted expert reviews with professional developers to assess reconstruction fidelity and prototyping efficiency. Our findings demonstrate that SPRITE streamlines development by automating tedious coding and resolving complex nesting. By facilitating rapid in-engine iteration, SPRITE effectively blurs the boundaries between artistic design and technical implementation in game development. Project page: https://baiyunshu.github.io/sprite.github.io/</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.03337</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.18591</guid>
|
||||||
<pubDate>Fri, 03 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 18 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts</title>
|
<title>Predicting integers from continuous parameters</title>
|
||||||
<link>https://arxiv.org/abs/2604.06505</link>
|
<link>https://arxiv.org/abs/2602.10751</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06505.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weiyue Li, Ruizhi Qian, Yi Li, Yongce Li, Yunfan Long, Jiahui Cai, Yan Luo, Mengyu Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language models (LLMs) are widely explored for reasoning-intensive research tasks, yet resources for testing whether they can infer scientific conclusions from structured biomedical evidence remain limited. We introduce MedConclusion, a large-scale dataset of 5.7M PubMed structured abstracts for biomedical conclusion generation. Each instance pairs the non-conclusion sections of an abstract with the original author-written conclusion, providing naturally occurring supervision for evidence-to-conclusion reasoning. MedConclusion also includes journal-level metadata such as biomedical category and SJR, enabling subgroup analysis across biomedical domains. As an initial study, we evaluate diverse LLMs under conclusion and summary prompting settings and score outputs with both reference-based metrics and LLM-as-a-judge. We find that conclusion writing is behaviorally distinct from summary writing, strong models remain closely clustered under current automatic metrics, and judge identity can substantially shift absolute scores. MedConclusion provides a reusable data resource for studying scientific evidence-to-conclusion reasoning. Our code and data are available at: https://github.com/Harvard-AI-and-Robotics-Lab/MedConclusion.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10751.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bas Maat, Peter Bloem</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We study the problem of predicting numeric labels that are constrained to the integers or to a subrange of the integers. For example, the number of up-votes on social media posts, or the number of bicycles available at a public rental station. While it is possible to model these as continuous values, and to apply traditional regression, this approach changes the underlying distribution on the labels from discrete to continuous. Discrete distributions have certain benefits, which leads us to the question whether such integer labels can be modeled directly by a discrete distribution, whose parameters are predicted from the features of a given instance. Moreover, we focus on the use case of output distributions of neural networks, which adds the requirement that the parameters of the distribution be continuous so that backpropagation and gradient descent may be used to learn the weights of the network. We investigate several options for such distributions, some existing and some novel, and test them on a range of tasks, including tabular learning, sequential prediction and image generation. We find that overall the best performance comes from two distributions: Bitwise, which represents the target integer in bits and places a Bernoulli distribution on each, and a discrete analogue of the Laplace distribution, which uses a distribution with exponentially decaying tails around a continuous mean.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06505</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10751</guid>
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.08537</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08537.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mu Nan, Muquan Yu, Weijian Mai, Jacob S. Prince, Hossein Adeli, Rui Zhang, Jiahang Cao, Benjamin Becker, John A. Pyles, Margaret M. Henderson, Chunfeng Song, Nikolaus Kriegeskorte, Michael J. Tarr, Xiaoqing Hu, Andrew F. Luo</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision. A field-wide goal is to achieve generalizable, cross-subject models. A major obstacle towards this goal is the substantial variability in neural representations across individuals, which has so far required training bespoke models or fine-tuning separately for each subject. To address this challenge, we introduce a meta-optimized approach for semantic visual decoding from fMRI that generalizes to novel subjects without any fine-tuning. By simply conditioning on a small set of image-brain activation examples from the new individual, our model rapidly infers their unique neural encoding patterns to facilitate robust and efficient visual decoding. Our approach is explicitly optimized for in-context learning of the new subject's encoding model and performs decoding by hierarchical inference, inverting the encoder. First, for multiple brain regions, we estimate the per-voxel visual response encoder parameters by constructing a context over multiple stimuli and responses. Second, we construct a context consisting of encoder parameters and response values over multiple voxels to perform aggregated functional inversion. We demonstrate strong cross-subject and cross-scanner generalization across diverse visual backbones without retraining or fine-tuning. Moreover, our approach requires neither anatomical alignment nor stimulus overlap. This work is a critical step towards a generalizable foundation model for non-invasive brain decoding.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.08537</guid>
|
|
||||||
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.11102</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.11102.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junfu Pu, Yuxin Chen, Teng Wang, Ying Shan</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Current multimodal large language models (MLLMs) have demonstrated remarkable capabilities in short-form video understanding, yet translating long-form cinematic videos into detailed, temporally grounded scripts remains a significant challenge. This paper introduces the novel video-to-script (V2S) task, aiming to generate hierarchical, scene-by-scene scripts encompassing character actions, dialogues, expressions, and audio cues. To facilitate this, we construct a first-of-its-kind human-annotated benchmark and propose a temporally-aware hierarchical evaluation framework. Furthermore, we present OmniScript, an 8B-parameter omni-modal (audio-visual) language model tailored for long-form narrative comprehension. OmniScript is trained via a progressive pipeline that leverages chain-of-thought supervised fine-tuning for plot and character reasoning, followed by reinforcement learning using temporally segmented rewards. Extensive experiments demonstrate that despite its parameter efficiency, OmniScript significantly outperforms larger open-source models and achieves performance comparable to state-of-the-art proprietary models, including Gemini 3-Pro, in both temporal localization and multi-field semantic accuracy.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.11102</guid>
|
|
||||||
<pubDate>Mon, 13 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 13 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Forge-UGC: FX optimization and register-graph engine for universal graph compiler</title>
|
<title>AgentSPEX: An Agent SPecification and EXecution Language</title>
|
||||||
<link>https://arxiv.org/abs/2604.16498</link>
|
<link>https://arxiv.org/abs/2604.13346</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16498.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Satyam Kumar, Saurabh Jha</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present Forge-UGC (FX Optimization and Register-Graph Engine for Universal Graph Compilation), a four-phase compiler for transformer deployment on heterogeneous accelerator hardware, validated on Intel AI Boost NPU. Existing frameworks such as OpenVINO and ONNX Runtime often use opaque compilation pipelines, limited pass-level visibility, and weak buffer management, which can lead to higher compilation cost and runtime overhead. Forge-UGC addresses this with a hardware-agnostic design that separates graph capture, optimization, intermediate representation lowering, and backend scheduling. Phase 1 captures graphs with torch.export at the ATen operator level, supporting modern transformer components such as rotary position embeddings, grouped-query attention, and SwiGLU without manual decomposition. Phase 2 applies six optimization passes: dead code elimination, common subexpression elimination, constant folding, attention fusion, operator fusion, and layout optimization, reducing graph node count by 14.2 to 21.9%. Phase 3 lowers the optimized graph into a typed intermediate representation with explicit virtual register assignments. Phase 4 performs liveness analysis, linear-scan buffer allocation, reducing peak buffer count by 30 to 48%, and device-affinity scheduling, reducing NPU-CPU transitions by 42 to 65%. Across six model families ranging from 125M to 8B parameters, evaluated on WikiText-103 and GLUE, Forge-UGC delivers 6.9 to 9.2x faster compilation than OpenVINO and ONNX Runtime, 18.2 to 35.7% lower inference latency, and 30.2 to 40.9% lower energy per inference. Fidelity is preserved, with max absolute logit differences below 2.1e-5 and KL divergence below 8.4e-9. We also introduce Fusion Gain Ratio, Compilation Efficiency Index, and per-pass execution profiling for systematic evaluation of NPU compilation pipelines.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.13346.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengcheng Wang, Jerry Huang, Jiarui Yao, Rui Pan, Peizhi Niu, Yaowenqi Liu, Ruida Wang, Renhao Lu, Yuwei Guo, Tong Zhang</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making agent behavior potentially difficult to control. Orchestration frameworks such as LangGraph, DSPy, and CrewAI impose greater structure through explicit workflow definitions, but tightly couple workflow logic with Python, making agents difficult to maintain and modify. In this paper, we introduce AgentSPEX, an Agent SPecification and EXecution Language for specifying LLM-agent workflows with explicit control flow and modular structure, along with a customizable agent harness. AgentSPEX supports typed steps, branching and loops, parallel execution, reusable submodules, and explicit state management, and these workflows execute within an agent harness that provides tool access, a sandboxed virtual environment, and support for checkpointing, verification, and logging. Furthermore, we provide a visual editor with synchronized graph and workflow views for authoring and inspection. We include ready-to-use agents for deep research and scientific research, and we evaluate AgentSPEX on 7 benchmarks. Finally, we show through a user study that AgentSPEX provides a more interpretable and accessible workflow-authoring paradigm than a popular existing agent framework.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16498</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.13346</guid>
|
||||||
<pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding</title>
|
<title>Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2604.13313</link>
|
<link>https://arxiv.org/abs/2604.16054</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.13313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eun Woo Im, Dhruv Madhwal, Vivek Gupta</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Vision-Language Models demonstrate remarkable capabilities but often struggle with compositional reasoning, exhibiting vulnerabilities regarding word order and attribute binding. This limitation arises from a scarcity of informative samples needed to differentiate subtle semantic variations during contrastive pretraining. Although hard negative mining offers a promising remedy, existing methods lack explicit mechanisms to dictate which linguistic elements undergo modification. Instead of engineering generative architectures, this study establishes lexical concreteness as a fundamental determinant of negative sample efficacy. Modifying highly concrete terms generates more pronounced structural and visual discrepancies, providing a substantially stronger learning signal. Leveraging this principle, ConcretePlant is proposed to systematically isolate and manipulate perceptually grounded concepts. Analyses of the InfoNCE further reveals a severe gradient imbalance, where easily distinguishable pairs disproportionately overwhelm the optimization process and restrict the bandwidth available for nuanced learning. To resolve this degradation, the Cement loss is formulated utilizing a margin-based approach. By correlating psycholinguistic scores with sample difficulty, this objective dynamically calibrates the penalization applied to individual training pairs. Comprehensive evaluations substantiate these theoretical claims. The integrated framework, designated as Slipform, achieves state-of-the-art accuracy across diverse compositional evaluation benchmarks, general cross-modal retrieval, single and multi label linear probing.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16054.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti, Vineeth N Balasubramanian, Tanuja Ganu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's Eye", a multiple-choice benchmark of eight visuo-cognitive tasks inspired by classic human intelligence tests and organized under a novel "A-R-T" taxonomy: Abstraction, Relation, and Transformation. The tasks probe core processes of fluid intelligence such as pattern induction, analogical relation mapping, and mental transformation. We evaluate a diverse suite of closed-source and open-source MLLMs and compare their performance with human participants. Humans achieve 80% accuracy, while top performing MLLMs remain below 50%. Error analysis reveals failures in: (i) visual attention allocation, (ii) internal perceptual manipulation, and (iii) weak abstraction of underlying visual concepts. Our findings suggest that current MLLMs exhibit limited visuospatial reasoning capabilities, when compared with human participants, highlighting the need for more cognitively grounded evaluation frameworks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.13313</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.16054</guid>
|
||||||
<pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.14258</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.14258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wangjie Gan, Miao Pan, Linbo Xi, Wenqi Zhang, Jintao Chen, Jianwei Yin, Xuhong Zhang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we provide a training-dynamics analysis showing that SFT can be interpreted as a special case of policy gradient optimization with an extremely sparse implicit reward and unstable inverse-probability weighting, which together lead to single-path dependency, entropy collapse, and gradient explosion. Motivated by this diagnosis, we propose Group Fine-Tuning (GFT), a unified post-training framework that addresses these intrinsic limitations through two mechanisms: Group Advantage Learning, which constructs diverse response groups and derives normalized contrastive supervision to alleviate reward sparsity, and Dynamic Coefficient Rectification, which adaptively bounds inverse-probability weights to stabilize optimization while preserving efficient knowledge injection. Experiments demonstrate that GFT consistently surpasses SFT-based methods and yields policies that integrate more smoothly with subsequent RL training.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.14258</guid>
|
|
||||||
<pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Protecting Language Models Against Unauthorized Distillation through Trace Rewriting</title>
|
|
||||||
<link>https://arxiv.org/abs/2602.15143</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.15143.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinhang Ma, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models. However, unauthorized use of knowledge distillation takes unfair advantage of the considerable effort and cost put into developing frontier models. We investigate methods for modifying teacher-generated reasoning traces to achieve two objectives that deter unauthorized distillation: (1) anti-distillation, or degrading the training usefulness of query responses, and (2) API watermarking, which embeds verifiable signatures in student models. We introduce several approaches for dynamically rewriting a teacher's reasoning outputs while preserving answer correctness and semantic coherence. Two of these leverage the rewriting capabilities of LLMs, while others use gradient-based techniques. Our experiments show that a simple instruction-based rewriting approach achieves a strong anti-distillation effect while maintaining or even improving teacher performance. Furthermore, we show that our rewriting approach also enables embedding watermarks that can be reliably detected with essentially no false alarms. Our code is available at https://github.com/xhOwenMa/trace-rewriting.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.15143</guid>
|
|
||||||
<pubDate>Thu, 16 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.15579</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.15579.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yining Hong, Yining She, Eunsuk Kang, Christopher S. Timperley, Christian Kästner</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing mitigations, such as training-based methods and neural guardrails, improve agent reliability but cannot provide guarantees. We study symbolic guardrails as a practical path toward strong safety and security guarantees for AI agents. Our three-part study includes a systematic review of 80 state-of-the-art agent safety and security benchmarks to identify the policies they evaluate, an analysis of which policy requirements can be guaranteed by symbolic guardrails, and an evaluation of how symbolic guardrails affect safety, security, and agent success on τ^2-Bench, CAR-bench, and MedAgentBench. We find that 85\% of benchmarks lack concrete policies, relying instead on underspecified high-level goals or common sense. Among the specified policies, 74\% of policy requirements can be enforced by symbolic guardrails, often using simple, low-cost mechanisms. These guardrails improve safety and security without sacrificing agent utility. Overall, our results suggest that symbolic guardrails are a practical and effective way to guarantee some safety and security requirements, especially for domain-specific AI agents. We release all codes and artifacts at https://github.com/hyn0027/agent-symbolic-guardrails.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.15579</guid>
|
|
||||||
<pubDate>Thu, 16 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>KWBench: Measuring Unprompted Problem Recognition in Knowledge Work</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.15760</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.15760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ankit Maloo</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM identify a professional scenario before attempting to solve it. Existing frontier benchmarks have saturated, and most knowledge-work evaluations to date reduce to extraction or task completion against a specification. KWBench targets the step before that: recognizing the governing structure of the situation from raw inputs alone. The benchmark contains 223 tasks sourced from practitioners across acquisitions, contract negotiations, clinical pharmacy, organizational politics, fraud analysis, and incentive design. Each task encodes a formal game-theoretic pattern (principal-agent conflict, signaling, mechanism design failure, strategic omission, coalitional dynamics, strategic interdependence) and carries structured ground truth recording the expert reading of the situation and the anticipated failure modes. Models receive raw data and a task prompt with no indication of problem type. Scoring is a three-tier rubric gated by a mandatory conjunctive check. Mandatory criteria encode the predicted wrong paths. We evaluate 16 models. The best model passes on 27.9% of tasks. The top two models agree on only 31.7% of their passes. Among the top 8, 44 tasks are solved by exactly one model; routing across the top 8 covers 50.7% of the benchmark, nearly double the best single model. Conditional on passing, quality scores converge (approx 83% across models); unconditional scores do not. Same models articulate the relevant game-theoretic concept correctly when asked, then fail to apply it unprompted. We release KWBench to shift how frontier models are evaluated on knowledge work, scoring them on whether they recognize the right problem from the situation alone, not only on how well they execute once the problem has been framed for them.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.15760</guid>
|
|
||||||
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models</title>
|
<title>Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2511.10262</link>
|
<link>https://arxiv.org/abs/2604.16060</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.10262.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> He Zhang, Wenqian Cui, Haoning Xu, Xiaohui Li, Lei Zhu, Haoli Bai, Shaohua Ma, Irwin King</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Full-Duplex Speech Language Models (FD-SLMs) enable real-time, overlapping conversational interactions, offering a more dynamic user experience compared to traditional half-duplex models. However, existing benchmarks primarily focus on evaluating single-round interactions, neglecting the complexities of multi-round communication. Evaluating FD-SLMs in multi-round settings poses significant challenges, including blurred turn boundaries in communication and context inconsistency during model inference. Also, existing benchmarks often focus solely on evaluating conversational features, neglecting other critical aspects. To address these gaps, we introduce MTR-DuplexBench, a novel benchmark designed for a comprehensive multi-round evaluation of FD-SLMs. MTR-DuplexBench not only segments continuous full-duplex dialogues into discrete turns for turn-by-turn assessment but also incorporates various evaluation aspects, including conversational features, dialogue quality, instruction following, and safety. Experimental results reveal that current FD-SLMs face difficulties in maintaining consistent performance across multiple rounds and evaluation dimensions, highlighting the necessity and effectiveness of our benchmark. Code and data are available at: https://github.com/ZhangHe0918/MTR-DuplexBench</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16060.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian, Tanuja Ganu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Multimodal Reasoning Models (MRMs) leveraging Chain-of-Thought (CoT) based thinking have revolutionized mathematical and logical problem-solving. However, we show that this paradigm struggles with generalized spatial intelligence. We perform a comprehensive evaluation of seventeen models across thirteen spatial benchmarks and identify a critical gap: CoT prompting consistently degrades performance in visual spatial reasoning. Furthermore, through a novel No-Image++ ablation, we demonstrate that MRMs and CoT prompted MLMs suffer from severe shortcut learning, and hallucinate visual details from textual priors even when the image is absent. These findings challenge the efficacy of text-only CoT for spatial tasks and underscore the need for vision-centric reasoning paradigms.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.10262</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.16060</guid>
|
||||||
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Geometric coherence of single-cell CRISPR perturbations reveals regulatory architecture and predicts cellular stress</title>
|
<title>Target-Oriented Pretraining Data Selection via Neuron-Activated Graph</title>
|
||||||
<link>https://arxiv.org/abs/2604.16642</link>
|
<link>https://arxiv.org/abs/2604.15706</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prashant C. Raju</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Genome engineering has achieved remarkable sequence-level precision, yet predicting the transcriptomic state that a cell will occupy after perturbation remains an open problem. Single-cell CRISPR screens measure how far cells move from their unperturbed state, but this effect magnitude ignores a fundamental question: do the cells move together? Two perturbations with identical magnitude can produce qualitatively different outcomes if one drives cells coherently along a shared trajectory while the other scatters them across expression space. We introduce a geometric stability metric, Shesha, that quantifies the directional coherence of single-cell perturbation responses as the mean cosine similarity between individual cell shift vectors and the mean perturbation direction. Across five CRISPR datasets (2,200+ perturbations spanning CRISPRa, CRISPRi, and pooled screens), stability correlates strongly with effect magnitude (Spearman ρ=0.75-0.97), with a calibrated cross-dataset correlation of 0.97. Crucially, discordant cases where the two metrics decouple expose regulatory architecture: pleiotropic master regulators such as CEBPA and GATA1 pay a "geometric tax," producing large but incoherent shifts, while lineage-specific factors such as KLF1 produce tightly coordinated responses. After controlling for magnitude, geometric instability is independently associated with elevated chaperone activation (HSPA5/BiP; ρ_{partial}=-0.34 and -0.21 across datasets), and the high-stability/high-stress quadrant is systematically depleted. The magnitude-stability relationship persists in scGPT foundation model embeddings, confirming it is a property of biological state space rather than linear projection. Perturbation stability provides a complementary axis for hit prioritization in screens, phenotypic quality control in cell manufacturing, and evaluation of in silico perturbation predictions.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.15706.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijun Wang, Haoqin Tu, Weidong Zhou, Yiyang Zhou, Xiaohuan Zhou, Bingni Zhang, Weiguo Feng, Taifeng Wang, Cihang Xie, Fengze Liu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Everyday tasks come with a target, and pretraining models around this target is what turns them into experts. In this paper, we study target-oriented language model (LM) pretraining by introducing Neuron-Activated Graph Ranking (NAG-based Ranking), a training-free and interpretable framework for target pretraining data selection. Rather than using black-box representations, our approach directly characterizes each target input by a sparse set of high-impact neurons in any off-the-shelf LLMs. Concretely, we quantify neuron impact and select the most influential neurons across layers into a compact Neuron-Activated Graph (NAG), and rank candidate data by NAG similarity to target examples. We conduct experiments across six benchmarks, where our NAG-based Ranking improves target-oriented pretraining by 4.9% on average over random sampling, and also outperforms state-of-the-art baselines by 5.3% accuracy on HellaSwag. It also remains effective under a more applicable multi-target setting, where our best setup surpasses two baselines by 1.1% and 4.1%, respectively. Furthermore, we provide a comprehensive analysis on why and how our NAG works, e.g., deactivating NAG-selected neurons (only 0.12% of all) causes a 23.5% performance collapse, and restricting NAG to the final layer incurs a 4.1% average drop, indicating that NAG captures a sparse "functional backbone" for learning target features. We release the code at https://github.com/asillycat/NAG.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16642</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.15706</guid>
|
||||||
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Modeling Sparse and Bursty Vulnerability Sightings: Forecasting Under Data Constraints</title>
|
<title>The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus</title>
|
||||||
<link>https://arxiv.org/abs/2604.16038</link>
|
<link>https://arxiv.org/abs/2604.16913</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16038.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cedric Bonhomme, Alexandre Dulaunoy</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Understanding and anticipating vulnerability-related activity is a major challenge in cyber threat intelligence. This work investigates whether vulnerability sightings, such as proof-of-concept releases, detection templates, or online discussions, can be forecast over time. Building on our earlier work on VLAI, a transformer-based model that predicts vulnerability severity from textual descriptions, we examine whether severity scores can improve time-series forecasting as exogenous variables. We evaluate several approaches for short-term forecasting of sightings per vulnerability. First, we test SARIMAX models with and without log(x+1) transformations and VLAI-derived severity inputs. Although these adjustments provide limited improvements, SARIMAX remains poorly suited to sparse, short, and bursty vulnerability data. In practice, forecasts often produce overly wide confidence intervals and sometimes unrealistic negative values. To better capture the discrete and event-driven nature of sightings, we then explore count-based methods such as Poisson regression. Early results show that these models produce more stable and interpretable forecasts, especially when sightings are aggregated weekly. We also discuss simpler operational alternatives, including exponential decay functions for short forecasting horizons, to estimate future activity without requiring long historical series. Overall, this study highlights both the potential and the limitations of forecasting rare and bursty cyber events, and provides practical guidance for integrating predictive analytics into vulnerability intelligence workflows.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Syed Muhammad Aqdas Rizvi</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Decentralized Autonomous Organizations (DAOs) are inclined explore Small Language Models (SLMs) as edge-native constitutional firewalls to vet proposals and mitigate semantic social engineering. While scaling inference-time compute (System 2) enhances formal logic, its efficacy in highly adversarial, cryptoeconomic governance environments remains underexplored. To address this, we introduce Sentinel-Bench, an 840-inference empirical framework executing a strict intra-model ablation on Qwen-3.5-9B. By toggling latent reasoning across frozen weights, we isolate the impact of inference-time compute against an adversarial Optimism DAO dataset. Our findings reveal a severe compute-accuracy inversion. The autoregressive baseline (System 1) achieved 100% adversarial robustness, 100% juridical consistency, and state finality in under 13 seconds. Conversely, System 2 reasoning introduced catastrophic instability, fundamentally driven by a 26.7% Reasoning Non-Convergence (cognitive collapse) rate. This collapse degraded trial-to-trial consensus stability to 72.6% and imposed a 17x latency overhead, introducing critical vulnerabilities to Governance Extractable Value (GEV) and hardware centralization. While rare (1.5% of adversarial trials), we empirically captured "Reasoning-Induced Sycophancy," where the model generated significantly longer internal monologues (averaging 25,750 characters) to rationalize failing the adversarial trap. We conclude that for edge-native SLMs operating under Byzantine Fault Tolerance (BFT) constraints, System 1 parameterized intuition is structurally and economically superior to System 2 iterative deliberation for decentralized consensus. Code and Dataset: https://github.com/smarizvi110/sentinel-bench</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16038</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.16913</guid>
|
||||||
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.16593</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16593.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Liu, Hongming Li, Melissa Xiaohui Qin, Qiankun Liu, Chao Huang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present SemanticQA, an evaluation suite designed to assess language models (LMs) in semantic phrase processing tasks. The benchmark consolidates existing multiword expression (MwE) resources and reorganizes them into a unified testbed. It covers both general lexical phenomena, such as lexical collocations, and three fine-grained categories: idiomatic expressions, noun compounds, and verbal constructions. Through SemanticQA, we assess LMs of diverse architectures and scales in extraction, classification, and interpretation tasks, as well as sequential task compositions. We reveal substantial performance variation, particularly on tasks requiring semantic reasoning, highlighting differences in reasoning efficacy and semantic understanding of LMs, providing insights for pushing LMs with stronger comprehension on non-trivial semantic phrases. The evaluation harness and data of SemanticQA are available at https://github.com/jacklanda/SemanticQA.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16593</guid>
|
|
||||||
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>VoxMind: An End-to-End Agentic Spoken Dialogue System</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.15710</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.15710.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Liang, Yifu Chen, Shengpeng Ji, Yijun Chen, Zhiyang Jia, Jingyu Lu, Fan Zhuo, Xueyi Pu, Yangzhuo Li, Zhou Zhao</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Recent end-to-end spoken dialogue models enable natural interaction. However, as user demands become increasingly complex, models that rely solely on conversational abilities often struggle to cope. Incorporating agentic capabilities is therefore essential: by enabling tool use, these models can extend their knowledge boundaries and better solve real-world tasks. Yet, existing research has largely concentrated on core perception and generation, with comparatively limited exploration of such tool-augmented extensions. To bridge this gap, we present VoxMind, an integrated framework designed to equip end-to-end spoken dialogue models with comprehensive agentic abilities. Leveraging our curated 470-hour AgentChat dataset, we incorporate a "Think-before-Speak" mechanism, enabling the model to internalize structured reasoning as a critical prerequisite for planning and response generation. Furthermore, to mitigate latency bottlenecks caused by large-scale tool integration, we propose a Multi-Agent Dynamic Tool Management architecture. By asynchronously delegating retrieval tasks to an auxiliary agent aligned with the main model's reasoning trajectory, this system effectively decouples inference latency from toolset size. Experimental results confirm that VoxMind achieves significant improvements in agent performance: compared with strong baselines, the task completion rate increases from 34.88% to 74.57%, outperforming Gemini-2.5-Pro on spoken agent tasks while preserving general conversational quality. The source code and associated data are publicly available at https://github.com/MM-Speech/VoxMind.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.15710</guid>
|
|
||||||
<pubDate>Fri, 17 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.16576</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongkang Li, Panagiotis Eustratiadis, Yixing Fan, Evangelos Kanoulas</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substantial performance gains and broad adoption. However, the robustness of these LLM-based retrievers remains underexplored. In this paper, we present the first systematic study of the robustness of state-of-the-art open-source LLM-based dense retrievers from two complementary perspectives: generalizability and stability. For generalizability, we evaluate retrieval effectiveness across four benchmarks spanning 30 datasets, using linear mixed-effects models to estimate marginal mean performance and disentangle intrinsic model capability from dataset heterogeneity. Our analysis reveals that while instruction-tuned models generally excel, those optimized for complex reasoning often suffer a ``specialization tax,'' exhibiting limited generalizability in broader contexts. For stability, we assess model resilience against both unintentional query variations~(e.g., paraphrasing, typos) and malicious adversarial attacks~(e.g., corpus poisoning). We find that LLM-based retrievers show improved robustness against typos and corpus poisoning compared to encoder-only baselines, yet remain vulnerable to semantic perturbations like synonymizing. Further analysis shows that embedding geometry (e.g., angular uniformity) provides predictive signals for lexical stability and suggests that scaling model size generally improves robustness. These findings inform future robustness-aware retriever design and principled benchmarking. Our code is publicly available at https://github.com/liyongkang123/Robust_LLM_Retriever_Eval.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16576</guid>
|
|
||||||
<pubDate>Fri, 17 Apr 2026 13:02:29 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.16943</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo Li, Ningyuan Deng, Tianyu Dong, Shaobo Wang, Shaolin Zhu, Lijie Wen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual information within images crucial for accurate image translation. This often leads to a modality gap between visual text inputs and textual inputs/outputs for image translation. Existing methods, primarily relying on instruction fine-tuning, risk parameter redundancy of pre-trained knowledge, hindering generalization performance. To address this, we introduce modality neuron-aware fine-tuning (MNAFT), a novel approach that takes advantage of the specialized roles of individual neurons within MLLMs for enhanced image translation. MNAFT identifies language-agnostic and language-specific neurons in both vision and language modules through an instruction-driven activation analysis, evaluating their importance in various translation tasks. We then perform selective fine-tuning, updating only the parameters of language-specific and language-agnostic neurons within the selected layers relevant to the target task, while preserving the knowledge encoded in other neurons and layers. Our extensive experiments on multiple benchmarks demonstrate that MNAFT significantly outperforms state-of-the-art image translation methods, including cascaded models, standard full fine-tuning, and parameter-efficient tuning techniques. Furthermore, we provide comprehensive analysis, including visualizations of neuron activations and clustering patterns, to offer insights into the roles of different neuron groups in mediating cross-modal understanding and facilitating accurate language-specific translation.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16943</guid>
|
|
||||||
<pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models</title>
|
<title>Understanding and Enforcing Weight Disentanglement in Task Arithmetic</title>
|
||||||
<link>https://arxiv.org/abs/2604.16902</link>
|
<link>https://arxiv.org/abs/2604.17078</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16902.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinru Yan, Boxi Cao, Yaojie Lu, Hongyu Lin, Weixiang Zhou, Le Sun, Xianpei Han</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Native Omni-modal Large Language Models (OLLMs) have shifted from pipeline architectures to unified representation spaces. However, this native integration gives rise to a critical yet underexplored phenomenon: modality preference. To bridge this gap, we first systematically quantify modality preference of OLLMs using a newly-curated conflict-based benchmark and the modality selection rate metric. Our evaluation of ten representative OLLMs reveals a notable paradigm shift: unlike the ``text-dominance'' of traditional VLMs, most OLLMs exhibit a pronounced visual preference. To further understand the underlying mechanism, we conduct layer-wise probing and demonstrate that such modality preference is not static but emerges progressively in the mid-to-late layers. Building upon these insights, we leverage these internal signals to diagnose cross-modal hallucinations, achieving competitive performance across three downstream multi-modal benchmarks without task-specific data. Our work provides both a mechanistic understanding and a practical tool for building more trustworthy OLLMs. Our code and related resources are publicly available at: https://github.com/icip-cas/OmniPreference</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17078.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shangge Liu, Yuehan Yin, Lei Wang, Qi Fan, Yinghuan Shi, Wenbin Li, Yang Gao, Dacheng Tao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Task arithmetic provides an efficient, training-free way to edit pre-trained models, yet lacks a fundamental theoretical explanation for its success. The existing concept of ``weight disentanglement" describes the ideal outcome of non-interfering task composition but does not reveal its underlying cause. Crucially, what intrinsic properties of the pre-trained model (θ_0) or the task vectors (τ_t) enable this disentanglement remains underexplored. In this paper, we introduce Task-Feature Specialization (TFS), a model's ability to allocate distinct internal features to different tasks, as the fundamental principle. We first prove that TFS is a sufficient condition for weight disentanglement. More importantly, we find that TFS also gives rise to an observable geometric consequence: weight vector orthogonality. This positions TFS as the common cause for both the desired functional outcome (disentanglement) and a measurable geometric property (orthogonality). This relationship provides the key insight for our method: since the abstract TFS property is intractable to enforce directly, we can instead promote weight disentanglement by shaping its concrete geometric consequence, orthogonality. Therefore, we propose OrthoReg, a simple and effective regularization method that actively enforces an internal orthogonal structure on weight updates (ΔW) that constitute τ_t during fine-tuning. And we theoretically prove that OrthoReg promotes disentanglement. Extensive experiments demonstrate that OrthoReg consistently and significantly enhances the performance of various task arithmetic methods. Code is available at https://github.com/RL-MIND/OrthoReg{https://github.com/RL-MIND/OrthoReg}.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16902</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.17078</guid>
|
||||||
<pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sat, 18 Apr 2026 17:34:56 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)</title>
|
<title>MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation</title>
|
||||||
<link>https://arxiv.org/abs/2604.17091</link>
|
<link>https://arxiv.org/abs/2604.17435</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17091.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqing Liang, Jinyi Han, Weijia Li, Xinyi Wang, Zhoujia Zhang, Zishang Jiang, Ying Liao, Tingyun Li, Ying Huang, Hao Shen, Hanyu Wu, Fang Guo, Keyi Wang, Zhonghua Hong, Zhiyu Lu, Lipeng Ma, Sihang Jiang, Yanghua Xiao</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for decision-making. At the same time, useful experience gained from tasks is often lost across episodes. We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget. We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: context information density maximization. GA implements this through four closely connected components: a minimal atomic tool set that keeps the interface simple, a hierarchical on-demand memory that only shows a small high-level view by default, a self-evolution mechanism that turns verified past trajectories into reusable SOPs and executable code, and a context truncation and compression layer that maintains information density during long executions. Across task completion, tool use efficiency, memory effectiveness, self-evolution, and web browsing, GA consistently outperforms leading agent systems while using significantly fewer tokens and interactions, and it continues to evolve over time. Project: https://github.com/lsdefine/GenericAgent</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17435.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Szu-Chi Chen, I-Ning Tsai, Yi-Cheng Lin, Sung-Feng Huang, Hung-yi Lee</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent Speech-to-Speech Translation (S2ST) systems achieve strong semantic accuracy yet consistently strip away non-verbal vocalizations (NVs), such as laughter and crying that convey pragmatic intent, which severely limits real-world utility. We address this via three contributions. First, we propose a synthesis pipeline for building scalable expressive datasets to overcome the data scarcity limitation. Second, we propose MoVE, a Mixture-of-LoRA-Experts architecture with expressive-specialized adapters and a soft-weighting router that blends experts for capturing hybrid expressive states. Third, we show pretrained AudioLLMs enable striking data efficiency: 30 minutes of curated data is enough for strong performance. On English-Chinese S2ST, while comparing with strong baselines, MoVE reproduces target NVs in 76% of cases and achieves the highest human-rated naturalness and emotional fidelity among all compared systems, where existing S2ST systems preserve at most 14% of NVs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17091</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.17435</guid>
|
||||||
<pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.16830</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16830.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Qinyuan Ye, Caiming Xiong, Chien-Sheng Wu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps models in severe overconfidence. We trace this failure to an information mismatch: teacher supervision is formed under privileged context available during training, whereas the deployed model must report confidence using only deployment-time information. We formalize this perspective theoretically, showing that teacher-conditioned success is generally not a valid target for deployment-time confidence and that helpful privileged context induces entropy collapse and a systematic optimism bias. To address this, we propose a calibration-aware OPD framework, CaOPD, that estimates empirical confidence from model rollouts, replaces self-reported confidence with this student-grounded target, and distills the revised response through the same self-distillation pipeline. Experiments across various models and domains show that CaOPD achieves Pareto-optimal calibration while maintaining competitive capability, generalizing robustly under out-of-distribution and continual learning. Our findings highlight that capability distillation does not imply calibrated confidence, and that confidence should be treated as an essential objective in post-training. Code: https://github.com/SalesforceAIResearch/CaOPD</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16830</guid>
|
|
||||||
<pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Crowded in B-Space: Calibrating Shared Directions for LoRA Merging</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.16826</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16826.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixuan Tang, Yi Yang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Merging separately trained LoRA adapters is a practical alternative to joint multi-task training, but it often hurts performance. Existing methods usually treat the LoRA update ΔW = BA as a single object and do not distinguish the two LoRA matrices. We show that the main source of LoRA merge interference comes from the output-side matrix B. Across tasks, B repeatedly uses a small set of shared directions, while A remains much more task-specific. As a result, the merged adapter overemphasizes these shared directions, and task-specific information is lost. We propose Pico (Pre-merge interference calibration in output-space), a data-free method that calibrates B before merge by downscaling over-shared directions and then rescaling the merged update. Pico plugs directly into existing merging methods such as Task Arithmetic, TIES, and TSV-M. Across eight different benchmarks from math, coding, finance, and medical domains, Pico improves average accuracy by 3.4-8.3 points over the corresponding base method and achieves the best overall average performance. Pico also enables merged adapters to outperform the LoRA trained with all task data. These results show that LoRA merging works better when the two LoRA matrices are treated separately.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16826</guid>
|
|
||||||
<pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>EasyVideoR1: Easier RL for Video Understanding</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.16893</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16893.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuanyu Qin, Chenxu Yang, Qingyi Si, Naibin Gu, Dingyu Yao, Zheng Lin, Peng Fu, Nan Duan, Jiaqi Wang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve into natively multimodal architectures, extending RLVR to video understanding becomes increasingly important yet remains largely unexplored, due to the diversity of video task types, the computational overhead of repeatedly decoding and preprocessing high-dimensional visual inputs, and the difficulty of reproducible evaluation across numerous sensitive hyperparameters. Existing open-source RL training frameworks provide solid infrastructure for text and image scenarios but lack systematic optimizations tailored for video modality. In this work, we present EasyVideoR1, a complete and efficient reinforcement learning framework specifically designed for training large vision-language models on video understanding tasks. EasyVideoR1 makes the following contributions: (1) a full video RL training pipeline with offline preprocessing and tensor caching that eliminates redundant video decoding and yields a 1.47 times throughput improvement; (2) a comprehensive, task-aware reward system covering 11 distinct video and image problem types with unified routing and modular extension; (3) a mixed offline-online data training paradigm that combines curated high-quality trajectories with on-policy exploration, benefiting the learning of more challenging tasks; (4) joint image-video training with independently configurable pixel budgets, allowing the two modalities to mutually reinforce each other; and (5) an asynchronous multi-benchmark evaluation framework covering 22 mainstream video understanding benchmarks, with reproduced accuracy closely aligned with officially reported scores.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.16893</guid>
|
|
||||||
<pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>HSG: Hyperbolic Scene Graph</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.17454</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17454.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liyang Wang, Zeyu Zhang, Hao Tang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene graph embeddings in Euclidean space using contrastive learning and attention based association. However, Euclidean geometry does not explicitly capture hierarchical entailment relationships between places and objects, limiting the structural consistency of learned representations. To address this, we propose Hyperbolic Scene Graph (HSG), which learns scene graph embeddings in hyperbolic space where hierarchical relationships are naturally encoded through geometric distance. Our results show that HSG improves hierarchical structure quality while maintaining strong retrieval performance. The largest gains are observed in graph level metrics: HSG achieves a PP IoU of 33.17 and the highest Graph IoU of 33.51, outperforming the best AoMSG variant (25.37) by 8.14, highlighting the effectiveness of hyperbolic representation learning for scene graph modeling. Code: https://github.com/AIGeeksGroup/HSG.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17454</guid>
|
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Back to Repair: A Minimal Denoising Network\ for Time Series Anomaly Detection</title>
|
<title>UniMesh: Unifying 3D Mesh Understanding and Generation</title>
|
||||||
<link>https://arxiv.org/abs/2604.17388</link>
|
<link>https://arxiv.org/abs/2604.17472</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17388.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kadir-Kaan Özer, René Ebeling, Markus Enzweiler</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We introduce JuRe (Just Repair), a minimal denoising network for time series anomaly detection that exposes a central finding: architectural complexity is unnecessary when the training objective correctly implements the manifold-projection principle. JuRe consists of a single depthwise-separable convolutional residual block with hidden dimension 128, trained to repair corrupted time series windows and scored at inference by a fixed, parameter-free structural discrepancy function. Despite using no attention, no latent variable, and no adversarial component, JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR 0.404, 180 series, 17 datasets) and second on the UCR univariate archive by AUC-PR (0.198, 250 series), leading all neural baselines on AUC-PR and VUS-PR. Component ablation on TSB-AD identifies training-time corruption as the dominant factor (ΔAUC-PR = 0.047 on removal), confirming that the denoising objective, not network capacity, drives detection quality. Pairwise Wilcoxon signed-rank tests establish statistical significance against 21 of 25 baselines on TSB-AD. Code is available at the URL https://github.com/iis-esslingen/JuRe.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Huang, Yifeng Chen, Zeyu Zhang, Hao Tang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Recent advances in 3D vision have led to specialized models for either 3D understanding (e.g., shape classification, segmentation, reconstruction) or 3D generation (e.g., synthesis, completion, and editing). However, these tasks are often tackled in isolation, resulting in fragmented architectures and representations that hinder knowledge transfer and holistic scene modeling. To address these challenges, we propose UniMesh, a unified framework that jointly learns 3D generation and understanding within a single architecture. First, we introduce a novel Mesh Head that acts as a cross model interface, bridging diffusion based image generation with implicit shape decoders. Second, we develop Chain of Mesh (CoM), a geometric instantiation of iterative reasoning that enables user driven semantic mesh editing through a closed loop latent, prompting, and re generation cycle. Third, we incorporate a self reflection mechanism based on an Actor Evaluator Self reflection triad to diagnose and correct failures in high level tasks like 3D captioning. Experimental results demonstrate that UniMesh not only achieves competitive performance on standard benchmarks but also unlocks novel capabilities in iterative editing and mutual enhancement between generation and understanding. Code: https://github.com/AIGeeksGroup/UniMesh. Website: https://aigeeksgroup.github.io/UniMesh.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17388</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.17472</guid>
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forward</title>
|
<title>Speculative Decoding for Autoregressive Video Generation</title>
|
||||||
<link>https://arxiv.org/abs/2604.17273</link>
|
<link>https://arxiv.org/abs/2604.17397</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Samuel Sameer Tanguturi</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The most important architectural problem in AI is not the size of the model but the absence of a layer that carries forward what the model has come to understand. Sessions end. Context windows fill. Memory APIs return flat facts that the model has to reinterpret from scratch on every read. The result is intelligence that is powerful per session and amnesiac across time. This position paper argues that the layer which fixes this, the continuity layer, is the most consequential piece of infrastructure the field has not yet built, and that the engineering work to build it has begun in public. The formal evaluation framework for the property described here is the ATANT benchmark (arXiv:2604.06710), published separately with evaluation results on a 250-story corpus; a companion paper (arXiv:2604.10981) positions this framework against existing memory, long-context, and agentic-memory benchmarks. The paper defines continuity as a system property with seven required characteristics, distinct from memory and from retrieval; describes a storage primitive (Decomposed Trace Convergence Memory) whose write-time decomposition and read-time reconstruction produce that property; maps the engineering architecture to the theological pattern of kenosis and the symbolic pattern of Alpha and Omega, and argues this mapping is structural rather than metaphorical; proposes a four-layer development arc from external SDK to hardware node to long-horizon human infrastructure; examines why the physics limits now constraining the model layer make the continuity layer newly consequential; and argues that the governance architecture (privacy implemented as physics rather than policy, founder-controlled class shares on non-negotiable architectural commitments) is inseparable from the product itself.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17397.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuezhou Hu, Jintao Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Autoregressive video diffusion is emerging as a promising paradigm for streaming video synthesis, with step distillation serving as the primary means of accelerating inference. Whether speculative decoding, the dominant acceleration strategy for large language models, can be effectively adapted to autoregressive video generation remains an open question, because video blocks are continuous spatiotemporal tensors with no token-level distribution for exact rejection sampling. We introduce SDVG, which brings speculative decoding to block-based autoregressive video diffusion by replacing token verification with an image-quality router. A 1.3B drafter proposes candidate blocks via four denoising steps; each block is VAE-decoded and scored by ImageReward using worst-frame aggregation--taking the minimum per-frame reward to catch single-frame artifacts that averaging would mask. Blocks scoring above a fixed threshold tau are accepted into the 14B target's KV cache; the rest are regenerated by the target. Two additional design choices prove critical: the first block is always force-rejected to anchor scene composition, and tau serves as a single knob that traces a smooth quality-speed Pareto frontier. On 1003 MovieGenVideoBench prompts (832x480), SDVG retains 98.1% of target-only VisionReward quality (0.0773 vs. 0.0788) at a 1.59x speedup with tau=-0.7, and reaches 2.09x at 95.7% quality retention--while consistently outperforming draft-only generation by over +17%. The framework is training-free, requires no architectural changes, and can be seamlessly integrated into existing autoregressive video generation pipelines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17273</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.17397</guid>
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories</title>
|
<title>Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers</title>
|
||||||
<link>https://arxiv.org/abs/2604.17596</link>
|
<link>https://arxiv.org/abs/2604.17632</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17596.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ivan Bercovich, Ivgeni Segal, Kexun Zhang, Shashwat Saxena, Aditi Raghunathan, Ziqian Zhong</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline trajectories across three frontier models (Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.4). Each entry preserves the original task definition alongside full attack trajectories that show how the verifier was bypassed. It also includes cases where the task was not solved as intended. The tasks span system administration, machine learning, software engineering, and security challenges; the exploits range from simple output spoofing to stack-frame introspection, standard-library patching, and rootkit-style binary hijacking. Crucially, these exploits are specific to each task, rather than the evaluation harness, making them harder to patch. We also present a monitorability study in which hack trajectories are sanitized or stripped of reasoning traces and then scored by an LLM judge, showing that detection degrades meaningfully when chain-of-thought is removed (AUC drops from 0.97 to 0.92). The data set is publicly available at https://github.com/few-sh/terminal-wrench.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17632.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingcheng Zeng, Yuheng Lu, Zeqi Zhou, Heli Qi, Puxuan Yu, Fuheng Zhao, Hitomi Yanaka, Weihao Xuan, Naoto Yokoya</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Code-switching is a pervasive linguistic phenomenon in global communication, yet modern information retrieval systems remain predominantly designed for, and evaluated within, monolingual contexts. To bridge this critical disconnect, we present a holistic study dedicated to code-switching IR. We introduce CSR-L (Code-Switching Retrieval benchmark-Lite), constructing a dataset via human annotation to capture the authentic naturalness of mixed-language queries. Our evaluation across statistical, dense, and late-interaction paradigms reveals that code-switching acts as a fundamental performance bottleneck, degrading the effectiveness of even robust multilingual models. We demonstrate that this failure stems from substantial divergence in the embedding space between pure and code-switched text. Scaling this investigation, we propose CS-MTEB, a comprehensive benchmark covering 11 diverse tasks, where we observe performance declines of up to 27%. Finally, we show that standard multilingual techniques like vocabulary expansion are insufficient to resolve these deficits completely. These findings underscore the fragility of current systems and establish code-switching as a crucial frontier for future IR optimization.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17596</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.17632</guid>
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>EvoMaster: A Foundational Agent Framework for Building Evolving Autonomous Scientific Agents at Scale</title>
|
<title>Mitigating Multimodal Hallucination via Phase-wise Self-reward</title>
|
||||||
<link>https://arxiv.org/abs/2604.17406</link>
|
<link>https://arxiv.org/abs/2604.17982</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17406.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Zhu, Yuzhu Cai, Zexi Liu, Cheng Wang, Fengyang Li, Wenkai Jin, Wanxu Liu, Zehao Bing, Bingyang Zheng, Jingyi Chai, Shuo Tang, Rui Ye, Yuwen Du, Xianghe Pang, Yaxin Du, Tingjia Miao, Yuzhi Zhang, Ruoxue Liao, Zhaohan Ding, Linfeng Zhang, Yanfeng Wang, Weinan E, Siheng Chen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped, and lack the capacity to learn from trial and error. To bridge this gap, we present EvoMaster, a foundational evolving agent framework engineered specifically for Agentic Science at Scale. Driven by the core principle of continuous self-evolution, EvoMaster empowers agents to iteratively refine hypotheses, self-critique, and progressively accumulate knowledge across experimental cycles, faithfully mirroring human scientific inquiry. Crucially, as a domain-agnostic base harness, EvoMaster is exceptionally easy to scale up -- enabling developers to build and deploy highly capable, self-evolving scientific agents for arbitrary disciplines in approximately 100 lines of code. Built upon EvoMaster, we incubated the SciMaster ecosystem across domains such as machine learning, physics, and general science. Evaluations on four authoritative benchmarks (Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience) demonstrate that EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3%, respectively. It comprehensively outperforms the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%, robustly validating its efficacy and generality as the premier foundational framework for the next generation of autonomous scientific discovery. EvoMaster is available at https://github.com/sjtu-sai-agents/EvoMaster.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17982.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zhang, Chuyang Sun, Kehai Chen, Xuefeng Bai, Yang Xiang, Min Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Vision-Language Models (LVLMs) still struggle with vision hallucination, where generated responses are inconsistent with the visual input. Existing methods either rely on large-scale annotated data for fine-tuning, which incurs massive computational overhead, or employ static post-hoc strategies that overlook the dynamic nature of hallucination emergence. To address these, we introduce a new self-rewarding framework, enabling dynamic hallucination mitigation at inference time without external supervision. On the empirical side, we reveal that visual hallucination exhibits phase-wise dynamic patterns, peaking at the onset of each semantic phase. Drawing on these insights, we propose PSRD (Phase-wise \textbf{Self-Reward Decoding) for online hallucination correction guided by phase-wise self-reward signals. To reduce the cost of repeated self-evaluation during decoding, we distill the hallucination guidance signal from LVLMs into a lightweight reward model. The reward model subsequently provides on-the-fly guidance for targeted intervention during the decoding process, enabling precise hallucination suppression. The proposed PSRD significantly reduces the hallucination rate of LLaVA-1.5-7B by 50.0% and consistently outperforms existing post-hoc methods across five hallucination evaluation benchmarks for four LVLMs. Further analysis confirms that PSRD effectively mitigates hallucination propagation and achieves a highly controllable trade-off between strong performance and inference efficiency.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17406</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.17982</guid>
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>When Background Matters: Breaking Medical Vision Language Models by Transferable Attack</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.17318</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17318.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Akash Ghosh, Subhadip Baidya, Sriparna Saha, Xiuying Chen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model stealing or adversarial fine-tuning, while transferable attacks from natural images introduce visible distortions that clinicians can easily detect. To address this, we propose MedFocusLeak, a highly transferable black-box multimodal attack that induces incorrect yet clinically plausible diagnoses while keeping perturbations imperceptible. The method injects coordinated perturbations into non-diagnostic background regions and employs an attention distraction mechanism to shift the model's focus away from pathological areas. Extensive evaluations across six medical imaging modalities show that MedFocusLeak achieves state-of-the-art performance, generating misleading yet realistic diagnostic outputs across diverse VLMs. We further introduce a unified evaluation framework with novel metrics that jointly capture attack success and image fidelity, revealing a critical weakness in the reasoning capabilities of modern clinical VLMs.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17318</guid>
|
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.17338</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wang Bill Zhu, Miaosen Chai, Shangshang Wang, Yejia Liu, Song Bian, Honghua Dong, Willie Neiswanger, Robin Jia</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise debugging, we introduce the Precise Debugging Benchmark (PDB) framework, which automatically converts any coding dataset into a debugging benchmark with precision-aware evaluation. PDB generates buggy programs by synthesizing verified atomic bugs and composing them into multi-bug programs. We define two novel metrics, edit-level precision and bug-level recall, which measures how many necessary edits are made and how many bugs are resolved. We release two evaluation benchmarks: PDB-Single-Hard on single-line bugs, and PDB-Multi on multi-line bugs. Experiments show that frontier models, such as GPT-5.1-Codex and DeepSeek-V3.2-Thinking, achieve unit-test pass rates above 76% but exhibit precision below 45%, even when explicitly instructed to perform minimal debugging. Finally, we show that iterative and agentic debugging strategies do not substantially improve precision or recall, highlighting the need to rethink post-training pipelines for coding models.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17338</guid>
|
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.17609</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17609.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Leon Engländer, Sophia Althammer, Ahmet Üstün, Matthias Gallé, Tom Sherborne</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should naturally lead to a model exploiting its own discoveries. We show that this assumption is false for current LLM-based agents, which struggle to reflect or react to unexpected information. Across three benchmarks (Terminal-Bench, SWE-Bench, AppWorld), we inject complete task solutions into the agent environments to deliberately expose a task's solution to a model. While agents discover these solutions on Terminal-Bench in 79-81% of runs, they interact, or exploit, them in only 37-50% of cases. This gap is starkest in AppWorld: agents see documentation stating that a command "returns the complete solution to this task" in over 90% of attempts but exploit this in fewer than 7% of trials. We show that agents lack what we call environmental curiosity: the capability to recognize and investigate unexpected but relevant observations in response to environmental stimuli. We identify three main factors influencing environmental curiosity: available tools in the agent scaffold, test-time compute, and training data distribution. Our findings identify configurations that maximize curiosity also achieve the best performance on the unmodified benchmarks. Yet even jointly optimized agents still ignore discovered solutions in the majority of trials: current agents use the environment to fetch expected information, but not to revise their strategy or maximally exploit useful stimuli.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17609</guid>
|
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.17308</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17308.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziao Zhang, Kou Shi, Shiting Huang, Avery Nie, Yu Zeng, Yiming Zhao, Zhen Fang, Qishen Su, Haibo Qiu, Wei Yang, Qingnan Ren, Shun Zou, Wenxuan Huang, Lin Chen, Zehui Chen, Feng Zhao</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills, leaving open whether they can discover skills from experience, repair them after failure, and maintain a coherent library over time. We introduce SkillFlow, a benchmark of 166 tasks across 20 families in which task construction within each family follows a Domain-Agnostic Execution Flow (DAEF) that defines an agent workflow framework, allowing these tasks to share a consistent workflow. Agents are evaluated under an Agentic Lifelong Learning protocol in which they begin without skills, solve tasks sequentially within each family, externalize lessons through trajectory- and rubric-driven skill patches, and carry the updated library forward. Experiments reveal a substantial capability gap. For Claude Opus 4.6, lifelong skill evolution improves task success from 62.65% to 71.08% (+8.43 points). However, high skill usage does not necessarily imply high utility: Kimi K2.5 gains only +0.60 points despite 66.87% skill usage, while Qwen-Coder-Next reaches only a 44.58% task completion rate and still regresses relative to the vanilla setting. SkillFlow contributes a structured testbed for this direction and an in-depth empirical analysis of skill discovery, patching, transfer, and their failure modes under lifelong evaluation.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17308</guid>
|
|
||||||
<pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Latent Preference Modeling for Cross-Session Personalized Tool Calling</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.17886</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17886.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yejin Yoon, Minseo Kim, Taeuk Kim</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental challenge for tool-augmented agents, as API execution typically requires complete arguments, highlighting the need for personalized tool calling. To study this problem, we introduce MPT, a benchmark comprising 265 multi-session dialogues that cover three challenges: Preference Recall, Preference Induction, and Preference Transfer. We also propose PRefine, a test-time memory-augmented method that represents user preferences as evolving hypotheses. Through a generate--verify--refine loop, it extracts reusable constraints from history and improves tool-calling accuracy while using only 1.24% of the tokens required by full-history prompting. These results indicate that robust personalization in agentic systems depends on memory that captures the reasons behind user choices, not just the choices themselves.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17886</guid>
|
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability</title>
|
<title>Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks</title>
|
||||||
<link>https://arxiv.org/abs/2604.17698</link>
|
<link>https://arxiv.org/abs/2604.17761</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17698.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prashant C. Raju</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behavioral control, and detecting when its internal structure degrades. We show that geometric stability, the consistency of a representation's pairwise distance structure, addresses both. Supervised Shesha variants that measure task-aligned geometric stability predict linear steerability with near-perfect accuracy (ρ= 0.89-0.97) across 35-69 embedding models and three NLP tasks, capturing unique variance beyond class separability (partial ρ= 0.62-0.76). A critical dissociation emerges: unsupervised stability fails entirely for steering on real-world tasks (ρapprox 0.10), revealing that task alignment is essential for controllability prediction. However, unsupervised stability excels at drift detection, measuring nearly 2times greater geometric change than CKA during post-training alignment (up to 5.23times in Llama) while providing earlier warning in 73\% of models and maintaining a 6times lower false alarm rate than Procrustes. Together, supervised and unsupervised stability form complementary diagnostics for the LLM deployment lifecycle: one for pre-deployment controllability assessment, the other for post-deployment monitoring.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17761.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rongyuan Tan, Jue Zhang, Zhuozhao Li, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or toy settings, leaving their behavior on commonly used benchmarks underexplored. To address this gap, we study contrastive, LRP-based attribution as a practical tool for analyzing LLM failures in realistic settings. We formulate failure analysis as contrastive attribution, attributing the logit difference between an incorrect output token and a correct alternative to input tokens and internal model states, and introduce an efficient extension that enables construction of cross-layer attribution graphs for long-context inputs. Using this framework, we conduct a systematic empirical study across benchmarks, comparing attribution patterns across datasets, model sizes, and training checkpoints. Our results show that this token-level contrastive attribution can yield informative signals in some failure cases, but is not universally applicable, highlighting both its utility and its limitations for realistic LLM failure analysis. Our code is available at: https://aka.ms/Debug-XAI.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17698</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.17761</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations</title>
|
<title>UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models</title>
|
||||||
<link>https://arxiv.org/abs/2604.17972</link>
|
<link>https://arxiv.org/abs/2604.18518</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17972.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Zhu, Huaixia Dou, Junhui Li, Lifan Guo, Feng Chen, Jinsong Su, Chi Zhang, Fang Kong</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Emotional Support Conversation (ESC) aims to assist individuals experiencing distress by generating empathetic and supportive dialogue. While prior work typically assumes that each supporter turn corresponds to a single strategy, real-world supportive communication often involves multiple strategies within a single utterance. In this paper, we revisit the ESC task by formulating it as multi-strategy utterance generation, where each utterance may contain one or more strategy-response pairs. We propose two generation methods: All-in-One, which predicts all strategy-response pairs in a single decoding step, and One-by-One, which iteratively generates strategy-response pairs until completion. Both methods are further enhanced with cognitive reasoning guided by reinforcement learning to improve strategy selection and response composition. We evaluate our models on the ESConv dataset under both utterance-level and dialogue-level settings. Experimental results show that our methods effectively model multi-strategy utterances and lead to improved supportive quality and dialogue success. To our knowledge, this work provides the first systematic empirical evidence that allowing multiple support strategies within a single utterance is both feasible and beneficial for emotional support conversations. All code and data will be publicly available at https://github.com/aliyun/qwen-dianjin.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18518.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Wang, Haoge Deng, Ting Pan, Yang Liu, Chengyuan Wang, Fan Zhang, Yonggang Qi, Xinlong Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that naively applying GRPO to UDM leads to training instability and marginal performance gains. To address this, we propose \Ours, the first framework to integrate UDM with RL. Our method is guided by two key insights: (i) treating the final clean sample as the action provides more accurate and stable optimization signals; and (ii) reconstructing trajectories via the diffusion forward process better aligns probability paths with the pretraining distribution. Additionally, we introduce two strategies, Reduced-Step and CFG-Free, to further improve training efficiency. \Ours significantly improves base model performance across multiple T2I tasks. Notably, GenEval accuracy improves from 69% to 96% and PickScore increases from 20.46 to 23.81, achieving state-of-the-art performance in both continuous and discrete settings. On the OCR benchmark, accuracy rises from 8% to 57%, further validating the generalization ability of our method. Code is available at https://github.com/Yovecent/UDM-GRPO{https://github.com/Yovecent/UDM-GRPO}.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17972</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.18518</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MARCO: Navigating the Unseen Space of Semantic Correspondence</title>
|
<title>MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge</title>
|
||||||
<link>https://arxiv.org/abs/2604.18267</link>
|
<link>https://arxiv.org/abs/2604.18164</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18267.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Claudia Cuttano, Gabriele Trivigno, Carlo Masone, Stefan Roth</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-parameter models generalize poorly beyond training keypoints, revealing a gap between benchmark performance and real-world usability, where queried points rarely match those seen during training. Building upon DINOv2, we introduce MARCO, a unified model for generalizable correspondence driven by a novel training framework that enhances both fine-grained localization and semantic generalization. By coupling a coarse-to-fine objective that refines spatial precision with a self-distillation framework, which expands sparse supervision beyond annotated regions, our approach transforms a handful of keypoints into dense, semantically coherent correspondences. MARCO sets a new state of the art on SPair-71k, AP-10K, and PF-PASCAL, with gains that amplify at fine-grained localization thresholds (+8.9 PCK@0.01), strongest generalization to unseen keypoints (+5.1, SPair-U) and categories (+4.7, MP-100), while remaining 3x smaller and 10x faster than diffusion-based approaches. Code is available at https://github.com/visinf/MARCO .</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18164.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sua Lee, Sanghee Park, Jinbae Im</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators-a paradigm known as MLLM-as-a-Judge. However, their reliability and vulnerabilities to biases remain underexplored. We find that many MLLM judges fail to reliably integrate key visual or textual cues, yielding unreliable evaluations when evidence is missing or mismatched, and exhibiting instability under semantically irrelevant perturbations. To address this, we systematically define Compositional Bias in MLLM-as-a-Judge systems and introduce MM-JudgeBias, a benchmark for evaluating it. MM-JudgeBias introduces controlled perturbations across Query, Image, and Response, and evaluates model behavior via two complementary metrics: Bias-Deviation (BD) for sensitivity and Bias-Conformity (BC) for stability. Our dataset of over 1,800 curated and refined multimodal samples, drawn from 29 source benchmarks, enables a fine-grained diagnosis of nine bias types across diverse tasks and domains. Experiments on 26 state-of-the-art MLLMs reveal systematic modality neglect and asymmetric evaluation tendencies, underscoring the need for more reliable judges.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18267</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.18164</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>River-LLM: Large Language Model Seamless Exit Based on KV Share</title>
|
<title>Dual-View Training for Instruction-Following Information Retrieval</title>
|
||||||
<link>https://arxiv.org/abs/2604.18396</link>
|
<link>https://arxiv.org/abs/2604.18845</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yingtao Shen, An Zou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency. Early Exit has emerged as a promising solution to accelerate inference by dynamically bypassing redundant layers. However, in decoder-only architectures, the efficiency of Early Exit is severely bottlenecked by the KV Cache Absence problem, where skipped layers fail to provide the necessary historical states for subsequent tokens. Existing solutions, such as recomputation or masking, either introduce significant latency overhead or incur severe precision loss, failing to bridge the gap between theoretical layer reduction and practical wall-clock speedup. In this paper, we propose River-LLM, a training-free framework that enables seamless token-level Early Exit. River-LLM introduces a lightweight KV-Shared Exit River that allows the backbone's missing KV cache to be naturally generated and preserved during the exit process, eliminating the need for costly recovery operations. Furthermore, we utilize state transition similarity within decoder blocks to predict cumulative KV errors and guide precise exit decisions. Extensive experiments on mathematical reasoning and code generation tasks demonstrate that River-LLM achieves 1.71 to 2.16 times of practical speedup while maintaining high generation quality.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18845.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingcheng Zeng, Puxuan Yu, Aman Mehta, Fuheng Zhao, Rajhans Samdani</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Instruction-following information retrieval (IF-IR) studies retrieval systems that must not only find documents relevant to a query, but also obey explicit user constraints such as required attributes, exclusions, or output preferences. However, most retrievers are trained primarily for semantic relevance and often fail to distinguish documents that match the topic from those that satisfy the instruction. We propose a dual-view data synthesis strategy based on polarity reversal: given a query, a document that is relevant under the instruction, and a hard negative that matches the query but violates the instruction, we prompt an LLM to generate a complementary instruction under which the two documents swap relevance labels. By presenting the same document pair under complementary instructions that invert their relevance labels, the training signal forces the retriever to reconsider the same candidate set through the instruction, rather than relying on fixed topical cues. On a 305M-parameter encoder, our method improves performance on the FollowIR benchmark by 45%, surpassing general-purpose embedding models of comparable or larger scale. Through head-to-head comparisons at matched data budgets, we further show that data diversity and instruction supervision play complementary roles: the former preserves general retrieval quality, while the latter improves instruction sensitivity. These results highlight the value of targeted data synthesis for building retrieval systems that are both broadly capable and instruction-aware.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18396</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.18845</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs</title>
|
<title>AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation</title>
|
||||||
<link>https://arxiv.org/abs/2604.18203</link>
|
<link>https://arxiv.org/abs/2604.18240</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Samuel G. Balter, Ethan Jerzak, Connor T. Jerzak</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal LLMs can accurately perceive numerical content across modalities yet fail to perform exact multi-digit multiplication when the identical underlying arithmetic problem is presented as numerals, number words, images, or in audio form. Because existing benchmarks often lack systematically paired instances across modalities, it remains difficult to compare genuine arithmetic limits within and across model families. We therefore introduce a controlled multimodal multiplication benchmark that factorially varies digit length, digit sparsity, representation (e.g., numerals vs. number words), and modality (text, rendered images, audio), with paired instances from a reproducible generator. We also define arithmetic load, C, as the product of the total and non-zero digit count as a compact, mechanistically motivated proxy for operation count. Across evaluations, accuracy falls sharply as C grows, often nearing zero by C > 100. Indeed, C remains predictive of performance across modalities and models, with R-squared often > 0.5, nearing the value from more complex measures of arithmetic load that count the number of intermediate arithmetic steps. A separate perception-versus-computation decomposition shows that multimodal degradation is primarily computational rather than perceptual: on matched-perception checks, models are near-perfect (> 99%) across modalities, even when multiplication accuracy drops. Beyond measuring when models fail, we ask which procedures they are predisposed to follow. We introduce a forced-completion loss probe that scores heuristic-specific reasoning prefixes--including columnar multiplication, distributive decomposition, and rounding/compensation. Here, decomposition is favored in both text and vision modalities; heuristic-specific LoRA adapters produce near-orthogonal updates yet degrade accuracy, indicating the base model maintains a well-tuned internal router.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi Gu, Hui Su, Xunliang Cai, Xiangnan He</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> As reinforcement learning continues to scale the training of large language model-based agents, reliably verifying agent behaviors in complex environments has become increasingly challenging. Existing approaches rely on rule-based verifiers or LLM-as-a-Judge models, which struggle to generalize beyond narrow domains. Agent-as-a-Judge addresses this limitation by actively interacting with environments and tools to acquire verifiable evidence, yet its capabilities remain underexplored. We introduce a benchmark AJ-Bench to systematically evaluate Agent-as-a-Judge across three domains-search, data systems, and graphical user interfaces-comprising 155 tasks and 516 annotated trajectories. The benchmark comprehensively assesses judge agents' abilities in information acquisition, state verification, and process verification. Experiments demonstrate consistent performance gains over LLM-as-a-Judge baselines, while also revealing substantial open challenges in agent-based verification. Our data and code are available at https://aj-bench.github.io/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18203</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.18240</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play</title>
|
<title>Micro Language Models Enable Instant Responses</title>
|
||||||
<link>https://arxiv.org/abs/2604.17696</link>
|
<link>https://arxiv.org/abs/2604.19642</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17696.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiachong Feng, Deyi Yin, Xiaocheng Feng, Yi Jiang, Libo Qin, Yangfan Ye, Lei Huang, Weitao Ma, Qiming Li, Yuxuan Gu, Bing Qin, Lingpeng Kong</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adaptive decision-making. However, existing self-play approaches rely solely on terminal game outcomes, providing no mechanism to distinguish transferable reasoning patterns from game-specific heuristics. We present STRATAGEM, which addresses two fundamental barriers to reasoning transfer: domain specificity, where learned patterns remain anchored in game semantics, and contextual stasis, where static game contexts fail to cultivate progressive reasoning. STRATAGEM selectively reinforces trajectories exhibiting abstract, domain-agnostic reasoning through a Reasoning Transferability Coefficient, while incentivizing adaptive reasoning development via a Reasoning Evolution Reward. Experiments across mathematical reasoning, general reasoning, and code generation benchmarks demonstrate substantial improvements, with particularly strong gains on competition-level mathematics where multi-step reasoning is critical. Ablation studies and human evaluation confirm that both components contribute to transferable reasoning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wen Cheng, Tuochao Chen, Karim Helwani, Sriram Srinivasan, Luke Zettlemoyer, Shyamnath Gollakota</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Edge devices such as smartwatches and smart glasses cannot continuously run even the smallest 100M-1B parameter language models due to power and compute constraints, yet cloud inference introduces multi-second latencies that break the illusion of a responsive assistant. We introduce micro language models (μLMs): ultra-compact models (8M-30M parameters) that instantly generate the first 4-8 words of a contextually grounded response on-device, while a cloud model completes it; thus, masking the cloud latency. We show that useful language generation survives at this extreme scale with our models matching several 70M-256M-class existing models. We design a collaborative generation framework that reframes the cloud model as a continuator rather than a respondent, achieving seamless mid-sentence handoffs and structured graceful recovery via three error correction methods when the local opener goes wrong. Empirical results show that μLMs can initiate responses that larger models complete seamlessly, demonstrating that orders-of-magnitude asymmetric collaboration is achievable and unlocking responsive AI for extremely resource-constrained devices. The model checkpoint and demo are available at https://github.com/Sensente/micro_language_model_swen_project.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17696</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19642</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration</title>
|
<title>Evaluation-driven Scaling for Scientific Discovery</title>
|
||||||
<link>https://arxiv.org/abs/2604.18131</link>
|
<link>https://arxiv.org/abs/2604.19341</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18131.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qifan Zhang, Dongyang Ma, Tianqing Fang, Jia Li, Jing Tang, Nuo Chen, Haitao Mi, Yan Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Most agents today ``self-evolve'' by following rewards and rules defined by humans. However, this process remains fundamentally dependent on external supervision; without human guidance, the evolution stops. In this work, we train agents to possess an intrinsic meta-evolution capability to spontaneously learn about unseen environments prior to task execution. To instill this ability, we design an outcome-based reward mechanism that measures how much an agent's self-generated world knowledge improves its success rate on downstream tasks. This reward signal is used exclusively during the training phase to teach the model how to explore and summarize effectively. At inference time, the agent requires no external rewards or human instructions. It spontaneously performs native self-evolution to adapt to unknown environments using its internal parameters. When applied to Qwen3-30B and Seed-OSS-36B, this shift to native evolution yields a 20% performance increase on WebVoyager and WebWalker. Most strikingly, the generated world knowledge even enables a compact 14B Qwen3 model to outperform the unassisted Gemini-2.5-Flash, establishing a new paradigm for truly evolving agents.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haotian Ye, Haowei Lin, Jingyi Tang, Yizhen Luo, Caiyin Yang, Chang Su, Rahul Thapa, Rui Yang, Ruihua Liu, Zeyu Li, Chong Gao, Dachao Ding, Guangrong He, Miaolei Zhang, Lina Sun, Wenyang Wang, Yuchen Zhong, Zhuohao Shen, Di He, Jianzhu Ma, Stefano Ermon, Tongyang Li, Xiaowen Chu, James Zou, Yuzhi Xu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively refine them. At the core of these trial-and-error loops lies evaluation: the process of obtaining feedback on candidate solutions via verifiers, simulators, or task-specific scoring functions. While prior work has highlighted the importance of evaluation, it has not explicitly formulated the problem of how evaluation-driven discovery loops can be scaled up in a principled and effective manner to push the boundaries of scientific discovery, a problem this paper seeks to address. We introduce Simple Test-time Evaluation-driven Scaling (SimpleTES), a general framework that strategically combines parallel exploration, feedback-driven refinement, and local selection, revealing substantial gains unlocked by scaling evaluation-driven discovery loops along the right dimensions. Across 21 scientific problems spanning six domains, SimpleTES discovers state-of-the-art solutions using gpt-oss models, consistently outperforming both frontier-model baselines and sophisticated optimization pipelines. Particularly, we sped up the widely used LASSO algorithm by over 2x, designed quantum circuit routing policies that reduce gate overhead by 24.5%, and discovered new Erdos minimum overlap constructions that surpass the best-known results. Beyond novel discoveries, SimpleTES produces trajectory-level histories that naturally supervise feedback-driven learning. When post-trained on successful trajectories, models not only improve efficiency on seen problems but also generalize to unseen problems, discovering solutions that base models fail to uncover. Together, our results establish effective evaluation-driven loop scaling as a central axis for advancing LLM-driven scientific discovery, and provide a simple yet practical framework for realizing these gains.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18131</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19341</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval</title>
|
<title>ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation</title>
|
||||||
<link>https://arxiv.org/abs/2604.18584</link>
|
<link>https://arxiv.org/abs/2604.19211</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18584.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaden Alshammari, Kevin Wen, Abrar Zainal, Mark Hamilton, Navid Safaei, Sultan Albarakati, William T. Freeman, Antonio Torralba</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Mathematical problem solving remains a challenging test of reasoning for large language and multimodal models, yet existing benchmarks are limited in size, language coverage, and task diversity. We introduce MathNet, a high-quality, large-scale, multimodal, and multilingual dataset of Olympiad-level math problems together with a benchmark for evaluating mathematical reasoning in generative models and mathematical retrieval in embedding-based systems. MathNet spans 47 countries, 17 languages, and two decades of competitions, comprising 30,676 expert-authored problems with solutions across diverse domains. In addition to the core dataset, we construct a retrieval benchmark consisting of mathematically equivalent and structurally similar problem pairs curated by human experts. MathNet supports three tasks: (i) Problem Solving, (ii) Math-Aware Retrieval, and (iii) Retrieval-Augmented Problem Solving. Experimental results show that even state-of-the-art reasoning models (78.4% for Gemini-3.1-Pro and 69.3% for GPT-5) remain challenged, while embedding models struggle to retrieve equivalent problems. We further show that retrieval-augmented generation performance is highly sensitive to retrieval quality; for example, DeepSeek-V3.2-Speciale achieves gains of up to 12%, obtaining the highest scores on the benchmark. MathNet provides the largest high-quality Olympiad dataset together with the first benchmark for evaluating mathematical problem retrieval, and we publicly release both the dataset and benchmark at https://mathnet.mit.edu.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19211.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiqin Yang, Zhenyuan Zhang, Xianzhang Jia, Jun Song, Wei Xue, Yonggang Zhang, Yike Guo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Current AI agent frameworks have made remarkable progress in automating individual tasks, yet all existing systems serve a single user. Human productivity rests on the social and organizational relationships through which people coordinate, negotiate, and delegate. When agents move beyond performing tasks for one person to representing that person in collaboration with others, the infrastructure for cross-user agent collaboration is entirely absent, let alone the governance mechanisms needed to secure it. We argue that the next frontier for AI agents lies not in stronger individual capability, but in the digitization of human collaborative relationships. To this end, we propose a human-symbiotic agent paradigm. Each user owns a permanently bound agent system that collaborates on the owner's behalf, forming a network whose nodes are humans rather than agents. This paradigm rests on three governance primitives. A layered identity architecture separates a Manager Agent from multiple context-specific Identity Agents; the Manager Agent holds global knowledge but is architecturally isolated from external communication. Scoped authorization enforces per-identity access control and escalates boundary violations to the owner. Action-level accountability logs every operation against its owner's identity and authorization, ensuring full auditability. We instantiate this paradigm in ClawNet, an identity-governed agent collaboration framework that enforces identity binding and authorization verification through a central orchestrator, enabling multiple users to collaborate securely through their respective agents.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18584</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19211</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>On the Reliability of Computer Use Agents</title>
|
<title>Accurate and scalable exchange-correlation with deep learning</title>
|
||||||
<link>https://arxiv.org/abs/2604.17849</link>
|
<link>https://arxiv.org/abs/2506.14665</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gonzalo Gonzalez-Pumariega, Saaket Agashe, Jiachen Yang, Ang Li, Xin Eric Wang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that succeeds once may fail on a repeated execution of the same task. This raises a fundamental question: if an agent can succeed at a task once, what prevents it from doing so reliably? In this work, we study the sources of unreliability in computer-use agents through three factors: stochasticity during execution, ambiguity in task specification, and variability in agent behavior. We analyze these factors on OSWorld using repeated executions of the same task together with paired statistical tests that capture task-level changes across settings. Our analysis shows that reliability depends on both how tasks are specified and how agent behavior varies across executions. These findings suggest the need to evaluate agents under repeated execution, to allow agents to resolve task ambiguity through interaction, and to favor strategies that remain stable across runs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.14665.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Giulia Luise, Chin-Wei Huang, Thijs Vogels, Derk P. Kooi, Sebastian Ehlert, Stephanie Lanius, Klaas J. H. Giesbertz, Amir Karton, Deniz Gunceler, Stefano Battaglia, Gregor N. C. Simm, P. Bernát Szabó, Megan Stanley, Wessel P. Bruinsma, Lin Huang, Xinran Wei, José Garrido Torres, Abylay Katbashev, Rodrigo Chavez Zavaleta, Bálint Máté, Sékou-Oumar Kaba, Roberto Sordillo, Yingrong Chen, David B. Williams-Young, Christopher M. Bishop, Jan Hermann, Rianne van den Berg, Paola Gori-Giorgi</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable properties remains fundamentally limited by the need to approximate the unknown exchange-correlation (XC) functional. The traditional paradigm for improving accuracy has relied on increasingly elaborate hand-crafted functional forms. This approach has led to a longstanding trade-off between computational efficiency and accuracy, which remains insufficient for reliable predictive modelling of laboratory experiments. Here we introduce Skala, a deep learning-based XC functional that surpasses state-of-the-art hybrid functionals in accuracy across the main-group chemistry benchmark set GMTKN55 with an error of 2.8 kcal/mol, while retaining the lower computational cost characteristic of semi-local DFT. This demonstrated departure from the historical trade-off between accuracy and efficiency is enabled by learning non-local representations of electronic structure directly from data, bypassing the need for increasingly costly hand-engineered features. Leveraging an unprecedented volume of high-accuracy reference data from wavefunction-based methods, we establish that modern deep learning enables systematically improvable neural exchange-correlation models as training datasets expand, positioning first-principles simulations to become progressively more predictive.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.17849</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.14665</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ClawEnvKit: Automatic Environment Generation for Claw-Like Agents</title>
|
<title>What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search</title>
|
||||||
<link>https://arxiv.org/abs/2604.18543</link>
|
<link>https://arxiv.org/abs/2604.19440</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18543.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xirui Li, Ming Li, Derry Xu, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh, Tianyi Zhou</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating diverse, verified environments on demand. To this end, we introduce ClawEnvKit, an autonomous generation pipeline that instantiates this formalism from natural language descriptions. The pipeline comprises three modules: (1) a parser that extracts structured generation parameters from natural language input; (2) a generator that produces the task specification, tool interface, and scoring configuration; and (3) a validator that enforces feasibility, diversity, structural validity, and internal consistency across the generated environments. Using ClawEnvKit, we construct Auto-ClawEval, the first large-scale benchmark for claw-like agents, comprising 1,040 environments across 24 categories. Empirically, Auto-ClawEval matches or exceeds human-curated environments on coherence and clarity at 13,800x lower cost. Evaluated across 4 model families and 8 agent harness frameworks, we find that harness engineering boosts performance by up to 15.7 percentage points over a bare ReAct baseline, completion remains the primary axis of variation with no model saturating the benchmark, and automated generation enables evaluation at a scale previously infeasible. Beyond static benchmarking, ClawEnvKit enables live evaluation: users describe a desired capability in natural language and obtain a verified environment on demand, turning evaluation into a continuous, user-driven process. The same mechanism serves as an on-demand training environment generator, producing task distributions that adapt to an agent's current weaknesses rather than being bounded by existing user logs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19440.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinhao Zhang, Xi Chen, François Portet, Maxime Peyrard</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent work has demonstrated the promise of orchestrating large language models (LLMs) within evolutionary and agentic optimization systems. However, the mechanisms driving these optimization gains remain poorly understood. In this work, we present a large-scale study of LLM-guided evolutionary search, collecting optimization trajectories for 15 LLMs across 8 tasks. Although zero-shot problem-solving ability correlates with final optimization outcomes, it explains only part of the variance: models with similar initial capability often induce dramatically different search trajectories and outcomes. By analyzing these trajectories, we find that strong LLM optimizers behave as local refiners, producing frequent incremental improvements while progressively localizing the search in semantic space. Conversely, weaker optimizers exhibit large semantic drift, with sporadic breakthroughs followed by stagnation. Notably, various measures of solution novelty do not predict final performance; novelty is beneficial only when the search remains sufficiently localized around high-performing regions of the solution space. Our results highlight the importance of trajectory analysis for understanding and improving LLM-based optimization systems and provide actionable insights for their design and training.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18543</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19440</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models</title>
|
<title>HP-Edit: A Human-Preference Post-Training Framework for Image Editing</title>
|
||||||
<link>https://arxiv.org/abs/2604.18224</link>
|
<link>https://arxiv.org/abs/2604.19406</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinping Lei, Xinyu Che, Junqi Xiong, Chenchen Zhang, Yukai Huang, Chenyu Zhou, Haoyang Huang, Minghao Liu, Letian Zhu, Hongyi Ye, Jinhua Hao, Ken Deng, Zizheng Zhan, Han Li, Dailin Li, Yifan Yao, Ming Sun, Zhaoxiang Zhang, Jiaheng Liu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large language models are rapidly evolving into interactive coding agents capable of end-to-end web coding, yet existing benchmarks evaluate only narrow slices of this capability, typically text-conditioned generation with static-correctness metrics, leaving visual fidelity, interaction quality, and codebase-level reasoning largely unmeasured. We introduce WebCompass, a multimodal benchmark that provides unified lifecycle evaluation of web engineering capability. Recognizing that real-world web coding is an iterative cycle of generation, editing, and repair, WebCompass spans three input modalities (text, image, video) and three task types (generation, editing, repair), yielding seven task categories that mirror professional workflows. Through a multi-stage, human-in-the-loop pipeline, we curate instances covering 15 generation domains, 16 editing operation types, and 11 repair defect types, each annotated at Easy/Medium/Hard levels. For evaluation, we adopt a checklist-guided LLM-as-a-Judge protocol for editing and repair, and propose a novel Agent-as-a-Judge paradigm for generation that autonomously executes generated websites in a real browser, explores interactive behaviors via the Model Context Protocol (MCP), and iteratively synthesizes targeted test cases, closely approximating human acceptance testing. We evaluate representative closed-source and open-source models and observe that: (1) closed-source models remain substantially stronger and more balanced; (2) editing and repair exhibit distinct difficulty profiles, with repair preserving interactivity better but remaining execution-challenging; (3) aesthetics is the most persistent bottleneck, especially for open-source models; and (4) framework choice materially affects outcomes, with Vue consistently challenging while React and Vanilla/HTML perform more strongly depending on task type.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19406.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fan Li, Chonghuinan Wang, Lina Lei, Yuping Qiu, Jiaqi Xu, Jiaxiu Jiang, Xinran Qin, Zhikai Chen, Fenglong Song, Zhixin Wang, Renjing Pei, Wangmeng Zuo</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further improved generation quality, efficiently applying Reinforcement Learning from Human Feedback (RLHF) to diffusion-based editing remains largely unexplored, due to a lack of scalable human-preference datasets and frameworks tailored to diverse editing needs. To fill this gap, we propose HP-Edit, a post-training framework for Human Preference-aligned Editing, and introduce RealPref-50K, a real-world dataset across eight common tasks and balancing common object editing. Specifically, HP-Edit leverages a small amount of human-preference scoring data and a pretrained visual large language model (VLM) to develop HP-Scorer--an automatic, human preference-aligned evaluator. We then use HP-Scorer both to efficiently build a scalable preference dataset and to serve as the reward function for post-training the editing model. We also introduce RealPref-Bench, a benchmark for evaluating real-world editing performance. Extensive experiments demonstrate that our approach significantly enhances models such as Qwen-Image-Edit-2509, aligning their outputs more closely with human preference.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18224</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19406</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>When Can LLMs Learn to Reason with Weak Supervision?</title>
|
<title>LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction</title>
|
||||||
<link>https://arxiv.org/abs/2604.18574</link>
|
<link>https://arxiv.org/abs/2604.19550</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18574.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Salman Rahman, Jingyan Shen, Anna Mordvina, Hamid Palangi, Saadia Gabriel, Pavel Izmailov</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large language models have achieved significant reasoning improvements through reinforcement learning with verifiable rewards (RLVR). Yet as model capabilities grow, constructing high-quality reward signals becomes increasingly difficult, making it essential to understand when RLVR can succeed under weaker forms of supervision. We conduct a systematic empirical study across diverse model families and reasoning domains under three weak supervision settings: scarce data, noisy rewards, and self-supervised proxy rewards. We find that generalization is governed by training reward saturation dynamics: models that generalize exhibit a prolonged pre-saturation phase during which training reward and downstream performance climb together, while models that saturate rapidly memorize rather than learn. We identify reasoning faithfulness, defined as the extent to which intermediate steps logically support the final answer, as the pre-RL property that predicts which regime a model falls into, while output diversity alone is uninformative. Motivated by these findings, we disentangle the contributions of continual pre-training and supervised fine-tuning, finding that SFT on explicit reasoning traces is necessary for generalization under weak supervision, while continual pre-training on domain data amplifies the effect. Applied together to Llama3.2-3B-Base, these interventions enable generalization across all three settings where the base model previously failed.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19550.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiakai Tang, Runfeng Zhang, Weiqiu Wang, Yifei Liu, Chuan Wang, Xu Chen, Yeqiu Yang, Jian Wu, Yuning Jiang, Bo Zheng</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Scaling Transformer-based click-through rate (CTR) models by stacking more parameters brings growing computational and storage overhead, creating a widening gap between scaling ambitions and the stringent industrial deployment constraints. We propose LoopCTR, which introduces a loop scaling paradigm that increases training-time computation through recursive reuse of shared model layers, decoupling computation from parameter growth. LoopCTR adopts a sandwich architecture enhanced with Hyper-Connected Residuals and Mixture-of-Experts, and employs process supervision at every loop depth to encode multi-loop benefits into the shared parameters. This enables a train-multi-loop, infer-zero-loop strategy where a single forward pass without any loop already outperforms all baselines. Experiments on three public benchmarks and one industrial dataset demonstrate state-of-the-art performance. Oracle analysis further reveals 0.02--0.04 AUC of untapped headroom, with models trained with fewer loops exhibiting higher oracle ceilings, pointing to a promising frontier for adaptive inference.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18574</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19550</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MultiWorld: Scalable Multi-Agent Multi-View Video World Models</title>
|
<title>RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2604.18564</link>
|
<link>https://arxiv.org/abs/2604.19321</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18564.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Wu, Jiwen Yu, Yingtian Zou, Xihui Liu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Video world models have achieved remarkable success in simulating environmental dynamics in response to actions by users or agents. They are modeled as action-conditioned video generation models that take historical frames and current actions as input to predict future frames. Yet, most existing approaches are limited to single-agent scenarios and fail to capture the complex interactions inherent in real-world multi-agent systems. We present MultiWorld, a unified framework for multi-agent multi-view world modeling that enables accurate control of multiple agents while maintaining multi-view consistency. We introduce the Multi-Agent Condition Module to achieve precise multi-agent controllability, and the Global State Encoder to ensure coherent observations across different views. MultiWorld supports flexible scaling of agent and view counts, and synthesizes different views in parallel for high efficiency. Experiments on multi-player game environments and multi-robot manipulation tasks demonstrate that MultiWorld outperforms baselines in video fidelity, action-following ability, and multi-view consistency. Project page: https://multi-world.github.io/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19321.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yusuf Çelebi, Yağız Asker, Özay Ezerceli, Mahmoud ElHussieni, Selva Taş, Reyhan Bayraktar, Fatma Betül Terzioğlu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Fine-tuning Large Language Models (LLMs) remains structurally uncertain despite parameter-efficient methods such as Low-Rank Adaptation (LoRA), as the layer-specific roles of internal representations are poorly understood, leading to heuristic decisions about where adaptation should be applied. We model the evolution of hidden states as a high-dimensional geometric trajectory and propose using the Ramer-Douglas-Peucker (RDP) algorithm, a parameter-free and training-free polygon simplification method that preserves global structural transitions while eliminating locally redundant changes, to identify critical breakpoints along the representation path. Crucially, we use these geometric pivots not merely for analysis, but as a direct decision signal for determining which layers should be adapted during parameter-efficient fine-tuning. By integrating this geometry-aware layer selection strategy into LoRA fine-tuning of Qwen3-8B-Base, we achieve superior performance on MMLU-Math using only 13 RDP-selected layers (81.67%), significantly outperforming both full 36-layer adaptation (79.32%) and random 13-layer selection (75.56%), as well as the baseline Qwen3-8B-Base model (74.25%). These results demonstrate that leveraging the intrinsic geometry of representation trajectories provides a robust, interpretable, and training-free signal for optimizing layer selection during model adaptation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18564</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19321</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>OpenGame: Open Agentic Coding for Games</title>
|
<title>SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing</title>
|
||||||
<link>https://arxiv.org/abs/2604.18394</link>
|
<link>https://arxiv.org/abs/2604.19587</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18394.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yilei Jiang, Jinyuan Hu, Qianyin Xiao, Yaozhi Zheng, Ruize Ma, Kaituo Feng, Jiaming Han, Tianshuo Peng, Kaixuan Fan, Manyuan Zhang, Xiangyu Yue</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Game development sits at the intersection of creative design and intricate software engineering, demanding the joint orchestration of game engines, real-time loops, and tightly coupled state across many files. While Large Language Models (LLMs) and code agents now solve isolated programming tasks with ease, they consistently stumble when asked to produce a fully playable game from a high-level design, collapsing under cross-file inconsistencies, broken scene wiring, and logical incoherence. We bridge this gap with OpenGame, the first open-source agentic framework explicitly designed for end-to-end web game creation. At its core lies Game Skill, a reusable, evolving capability composed of a Template Skill that grows a library of project skeletons from experience and a Debug Skill that maintains a living protocol of verified fixes - together enabling the agent to scaffold stable architectures and systematically repair integration errors rather than patch isolated syntax bugs. Powering this framework is GameCoder-27B, a code LLM specialized for game engine mastery through a three-stage pipeline of continual pre-training, supervised fine-tuning, and execution-grounded reinforcement learning. Since verifying interactive playability is fundamentally harder than checking static code, we further introduce OpenGame-Bench, an evaluation pipeline that scores agentic game generation along Build Health, Visual Usability, and Intent Alignment via headless browser execution and VLM judging. Across 150 diverse game prompts, OpenGame establishes a new state-of-the-art. We hope OpenGame pushes code agents beyond discrete software engineering problems and toward building complex, interactive real-world applications. Our framework will be fully open-sourced.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19587.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ying Zeng, Miaosen Luo, Guangyuan Li, Yang Yang, Ruiyang Fan, Linxiao Shi, Qirui Yang, Jian Zhang, Chengcheng Liu, Siming Zheng, Jinwei Chen, Bo Li, Peng-Tao Jiang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for adjusting image quality and camera parameters. However, this paradigm relies on explicit human instruction of aesthetic intent, which is often ambiguous, incomplete, or inaccessible to non-expert users. In this work, we propose SmartPhotoCrafter, an automatic photographic image editing method which formulates image editing as a tightly coupled reasoning-to-generation process. The proposed model first performs image quality comprehension and identifies deficiencies by the Image Critic module, and then the Photographic Artist module realizes targeted edits to enhance image appeal, eliminating the need for explicit human instructions. A multi-stage training pipeline is adopted: (i) Foundation pretraining to establish basic aesthetic understanding and editing capabilities, (ii) Adaptation with reasoning-guided multi-edit supervision to incorporate rich semantic guidance, and (iii) Coordinated reasoning-to generation reinforcement learning to jointly optimize reasoning and generation. During training, SmartPhotoCrafter emphasizes photo-realistic image generation, while supporting both image restoration and retouching tasks with consistent adherence to color- and tone-related semantics. We also construct a stage-specific dataset, which progressively builds reasoning and controllable generation, effective cross-module collaboration, and ultimately high-quality photographic enhancement. Experiments demonstrate that SmartPhotoCrafter outperforms existing generative models on the task of automatic photographic enhancement, achieving photo-realistic results while exhibiting higher tonal sensitivity to retouching instructions. Project page: https://github.com/vivoCameraResearch/SmartPhotoCrafter.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18394</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19587</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence</title>
|
<title>CityRAG: Stepping Into a City via Spatially-Grounded Video Generation</title>
|
||||||
<link>https://arxiv.org/abs/2604.18292</link>
|
<link>https://arxiv.org/abs/2604.19741</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18292.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanting Dong, Junting Lu, Junjie Huang, Wanjun Zhong, Longxiang Liu, Shijue Huang, Zhenyu Li, Yang Zhao, Xiaoshuai Song, Xiaoxi Li, Jiajie Jin, Yutao Zhu, Hanbin Wang, Fangyu Lei, Qinyu Luo, Mingyang Chen, Zehui Chen, Jiazhan Feng, Ji-Rong Wen, Zhicheng Dou</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting agents with scalable real-world services, but training robust agents remains limited by the lack of realistic environments and principled mechanisms for life-long learning. In this paper, we present Agent-World, a self-evolving training arena for advancing general agent intelligence through scalable environments. Agent-World has two main components: (1) Agentic Environment-Task Discovery, which autonomously explores topic-aligned databases and executable tool ecosystems from thousands of real-world environment themes and synthesizes verifiable tasks with controllable difficulty; and (2) Continuous Self-Evolving Agent Training, which combines multi-environment reinforcement learning with a self-evolving agent arena that automatically identifies capability gaps through dynamic task synthesis and drives targeted learning, enabling the co-evolution of agent policies and environments. Across 23 challenging agent benchmarks, Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines. Further analyses reveal scaling trends in relation to environment diversity and self-evolution rounds, offering insights for building general agent intelligence.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19741.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gene Chou, Charles Herrmann, Kyle Genova, Boyang Deng, Songyou Peng, Bharath Hariharan, Jason Y. Zhang, Noah Snavely, Philipp Henzler</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video generative models can produce a plausible sequence that is consistent with a text (T2V) or image (I2V) prompt. However, the capability to reconstruct the real world under arbitrary weather conditions and dynamic object configurations is essential for downstream applications including autonomous driving and robotics simulation. To this end, we present CityRAG, a video generative model that leverages large corpora of geo-registered data as context to ground generation to the physical scene, while maintaining learned priors for complex motion and appearance changes. CityRAG relies on temporally unaligned training data, which teaches the model to semantically disentangle the underlying scene from its transient attributes. Our experiments demonstrate that CityRAG can generate coherent minutes-long, physically grounded video sequences, maintain weather and lighting conditions over thousands of frames, achieve loop closure, and navigate complex trajectories to reconstruct real-world geography.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18292</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19741</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation</title>
|
<title>Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language</title>
|
||||||
<link>https://arxiv.org/abs/2604.18486</link>
|
<link>https://arxiv.org/abs/2604.19667</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18486.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinghui Lu, Jiayi Guan, Zhijian Huang, Jinlong Li, Guang Li, Lingdong Kong, Yingyan Li, Han Wang, Shaoqing Xu, Yuechen Luo, Fang Li, Chenxu Dang, Junli Wang, Tao Xu, Jing Wu, Jianhua Wu, Xiaoshuai Hao, Wen Zhang, Tianyi Jiang, Lingfeng Zhang, Lei Zhou, Yingbo Tang, Jie Wang, Yinfeng Gao, Xizhou Bu, Haochen Tian, Yihang Qiu, Feiyang Jia, Lin Liu, Yigu Ge, Hanbing Li, Yuannan Shen, Jianwei Cui, Hongwei Xie, Bing Wang, Haiyang Sun, Jingwei Zhao, Jiahui Huang, Pei Liu, Zeyu Zhu, Yuncheng Jiang, Zibin Guo, Chuhong Gong, Hanchao Leng, Kun Ma, Naiyang Wang, Guang Chen, Kuiyuan Yang, Hangjun Ye, Long Chen</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. At inference, the auxiliary decoders are discarded and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering state-of-the-art accuracy at answer-only latency, and providing direct evidence that tighter compression, when guided in both language and world-model supervision, produces more generalizable representations than verbose token-by-token reasoning. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Zhong, Buqiang Xu, Yijun Wang, Zifei Shan, Shuofei Qiao, Guozhou Zheng, Ningyu Zhang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely constructed through manual engineering: developers must carefully design workflows, write prompts for each step, and repeatedly revise the logic as requirements evolve-making development costly, time-consuming, and error-prone. To study whether large language models can automate this multi-round interaction process, we introduce Chat2Workflow, a benchmark for generating executable visual workflows directly from natural language, and propose a robust agentic framework to mitigate recurrent execution errors. Chat2Workflow is built from a large collection of real-world business workflows, with each instance designed so that the generated workflow can be transformed and directly deployed to practical workflow platforms such as Dify and Coze. Experimental results show that while state-of-the-art language models can often capture high-level intent, they struggle to generate correct, stable, and executable workflows, especially under complex or changing requirements. Although our agentic framework yields up to 5.34% resolve rate gains, the remaining real-world gap positions Chat2Workflow as a foundation for advancing industrial-grade automation. Code is available at https://github.com/zjunlp/Chat2Workflow.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18486</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19667</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation</title>
|
<title>ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning</title>
|
||||||
<link>https://arxiv.org/abs/2604.18168</link>
|
<link>https://arxiv.org/abs/2604.19254</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenxi Zhao, Chen Zhu, Xiaokun Feng, Aiming Hao, Jiashu Zhu, Jiachen Lei, Jiahong Wu, Xiangxiang Chu, Jufeng Yang</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an intuitive yet unexplored direction is to extend the condition from fixed class labels to flexible text inputs, enabling richer content creation. Compared to the limited class labels, text conditions pose greater challenges to the model's understanding capability, necessitating the effective integration of powerful text encoders into the MeanFlow framework. Surprisingly, although incorporating text conditions appears straightforward, we find that integrating powerful LLM-based text encoders using conventional training strategies results in unsatisfactory performance. To uncover the underlying cause, we conduct detailed analyses and reveal that, due to the extremely limited number of refinement steps in the MeanFlow generation, such as only one step, the text feature representations are required to possess sufficiently high discriminability. This also explains why discrete and easily distinguishable class features perform well within the MeanFlow framework. Guided by these insights, we leverage a powerful LLM-based text encoder validated to possess the required semantic properties and adapt the MeanFlow generation process to this framework, resulting in efficient text-conditioned synthesis for the first time. Furthermore, we validate our approach on the widely used diffusion model, demonstrating significant generation performance improvements. We hope this work provides a general and practical reference for future research on text-conditioned MeanFlow generation. The code is available at https://github.com/AMAP-ML/EMF.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19254.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xianming Li, Zongxi Li, Tsz-fung Andrew Lee, Jing Li, Haoran Xie, Qing Li</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Parameter-efficient fine-tuning (PEFT) reduces the training cost of full-parameter fine-tuning for large language models (LLMs) by training only a small set of task-specific parameters while freezing the pretrained backbone. However, existing approaches, such as Low-Rank Adaptation (LoRA), achieve adaptation by inserting independent low-rank perturbations directly to individual weights, resulting in a local parameterization of adaptation. We propose ShadowPEFT, a centralized PEFT framework that instead performs layer-level refinement through a depth-shared shadow module. At each transformer layer, ShadowPEFT maintains a parallel shadow state and evolves it repeatedly for progressively richer hidden states. This design shifts adaptation from distributed weight-space perturbations to a shared layer-space refinement process. Since the shadow module is decoupled from the backbone, it can be reused across depth, independently pretrained, and optionally deployed in a detached mode, benefiting edge computing scenarios. Experiments on generation and understanding benchmarks show that ShadowPEFT matches or outperforms LoRA and DoRA under comparable trainable-parameter budgets. Additional analyses on shadow pretraining, cross-dataset transfer, parameter scaling, inference latency, and system-level evaluation suggest that centralized layer-space adaptation is a competitive and flexible alternative to conventional low-rank PEFT.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.18168</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19254</guid>
|
||||||
<pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>PlayCoder: Making LLM-Generated GUI Code Playable</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.19742</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19742.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Peng, Wei Tao, Xin Yin, Chenhao Ying, Yuan Luo, Yiwen Guo</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Large language models (LLMs) have achieved strong results in code generation, but their ability to generate GUI applications, especially games, remains insufficiently studied. Existing benchmarks mainly evaluate correctness through test cases, which are inadequate for GUI applications because these systems are interactive, event-driven, and require correct state transitions across sequences of user actions. Their evaluation therefore should consider interaction flows and UI logic rather than only pass/fail outcomes. To study this problem, we introduce PlayEval, a repository-aware benchmark built from 43 multilingual GUI applications in Python, TypeScript, and JavaScript. Unlike prior GUI benchmarks that are difficult to adapt to desktop environments, PlayEval covers six major GUI application categories and directly supports code-generation evaluation. We further propose Play@k, a metric that measures whether at least one of *k* generated candidates can be played end-to-end without logical errors. To support reliable evaluation, we develop PlayTester, an LLM-based agent that performs task-oriented GUI playthroughs and detects logic violations automatically. Experiments on 10 state-of-the-art code LLMs show that, despite high compilation rates, they achieve near-zero Play@3, revealing major weaknesses in generating logically correct GUI applications. To address this limitation, we present PlayCoder, a multi-agent, repository-aware framework that generates, evaluates, and iteratively repairs GUI application code in a closed loop. PlayCoder substantially improves both functional correctness and semantic alignment for open-source and closed-source models, reaching up to 38.1% Exec@3 and 20.3% Play@3. Case studies further show that it can uncover silent logic bugs missed by traditional metrics and fix them through targeted edits.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19742</guid>
|
||||||
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>TEMPO: Scaling Test-time Training for Large Reasoning Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.19295</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyang Zhang, Xinke Kong, Haitao Wu, Qinghua Hu, Minghao Wu, Baosong Yang, Yu Cheng, Yun Luo, Ganqu Cui, Changqing Zhang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau quickly and do not benefit from additional test-time compute. Without external calibration, the self-generated reward signal increasingly drifts as the policy model evolves, leading to both performance plateaus and diversity collapse. We propose TEMPO, a TTT framework that interleaves policy refinement on unlabeled questions with periodic critic recalibration on a labeled dataset. By formalizing this alternating procedure through the Expectation-Maximization (EM) algorithm, we reveal that prior methods can be interpreted as incomplete variants that omit the crucial recalibration step. Reintroducing this step tightens the evidence lower bound (ELBO) and enables sustained improvement. Across diverse model families (Qwen3 and OLMO3) and reasoning tasks, TEMPO improves OLMO3-7B on AIME 2024 from 33.0% to 51.1% and Qwen3-14B from 42.3% to 65.8%, while maintaining high diversity.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19295</guid>
|
||||||
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.19747</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutian Chen, Shi Guo, Renbiao Jin, Tianshuo Yang, Xin Cai, Yawen Luo, Mingxin Yang, Mulin Yu, Linning Xu, Tianfan Xue</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusion-based approaches mitigates this issues by synthesizing novel views, but they often condition on only one or two capture frames, which restricts geometric consistency and limits scalability to large or diverse scenes. We propose AnyRecon, a scalable framework for reconstruction from arbitrary and unordered sparse inputs that preserves explicit geometric control while supporting flexible conditioning cardinality. To support long-range conditioning, our method constructs a persistent global scene memory via a prepended capture view cache, and removes temporal compression to maintain frame-level correspondence under large viewpoint changes. Beyond better generative model, we also find that the interplay between generation and reconstruction is crucial for large-scale 3D scenes. Thus, we introduce a geometry-aware conditioning strategy that couples generation and reconstruction through an explicit 3D geometric memory and geometry-driven capture-view retrieval. To ensure efficiency, we combine 4-step diffusion distillation with context-window sparse attention to reduce quadratic complexity. Extensive experiments demonstrate robust and scalable reconstruction across irregular inputs, large viewpoint gaps, and long trajectories.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19747</guid>
|
||||||
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.19636</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19636.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyang Luo, Xiaozhe Xin, Tao Feng, Xu Guo, Meiguang Jin, Junfeng Ma</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Synthesizing human--object interaction (HOI) videos has broad practical value in e-commerce, digital advertising, and virtual marketing. However, current diffusion models, despite their photorealistic rendering capability, still frequently fail on (i) the structural stability of sensitive regions such as hands and faces and (ii) physically plausible contact (e.g., avoiding hand--object interpenetration). We present CoInteract, an end-to-end framework for HOI video synthesis conditioned on a person reference image, a product reference image, text prompts, and speech audio. CoInteract introduces two complementary designs embedded into a Diffusion Transformer (DiT) backbone. First, we propose a Human-Aware Mixture-of-Experts (MoE) that routes tokens to lightweight, region-specialized experts via spatially supervised routing, improving fine-grained structural fidelity with minimal parameter overhead. Second, we propose Spatially-Structured Co-Generation, a dual-stream training paradigm that jointly models an RGB appearance stream and an auxiliary HOI structure stream to inject interaction geometry priors. During training, the HOI stream attends to RGB tokens and its supervision regularizes shared backbone weights; at inference, the HOI branch is removed for zero-overhead RGB generation. Experimental results demonstrate that CoInteract significantly outperforms existing methods in structural stability, logical consistency, and interaction realism.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19636</guid>
|
||||||
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.19748</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengting Chen, Zhengrui Chen, Yongchao Du, Zuan Gao, Taihang Hu, Jinsong Lan, Chao Lin, Yefeng Shen, Xingjian Wang, Zhao Wang, Zhengtao Wu, Xiaoli Xu, Zhengze Xu, Hao Yan, Mingzhou Zhang, Jun Zheng, Qinye Zhou, Xiaoyong Zhu, Bo Zheng</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scale virtual try-on system that is robust, realistic, versatile, and highly efficient. First, our system maintains a high success rate across challenging cases like extreme poses, severe illumination variations, motion blur, and other in-the-wild conditions. Second, it delivers highly photorealistic results with fine-grained details, faithfully preserving garment texture, material properties, and structural characteristics, while largely avoiding common AI-generated artifacts. Third, beyond apparel try-on, our model supports flexible multi-image composition (up to 6 reference images) across 8 fashion categories, with coordinated control over person identity and background. Fourth, to overcome the latency bottlenecks of commercial deployment, our system is heavily optimized for inference speed, delivering near real-time generation for a seamless user experience. These capabilities are enabled by an integrated system design spanning end-to-end model architecture, a scalable data engine, robust infrastructure, and a multi-stage training paradigm. Extensive evaluation and large-scale product deployment demonstrate that Tstars-Tryon1.0 achieves leading overall performance. To support future research, we also release a comprehensive benchmark. The model has been deployed at an industrial scale on the Taobao App, serving millions of users with tens of millions of requests.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.19748</guid>
|
||||||
|
<pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user