001 $Σ$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems arXiv Paper Peilin Feng, Suorong Yang et al. Yesterday 002 A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models arXiv Paper Xiangyu Yin, Tora Bodin et al. Yesterday 003 A Fuzzy Rule-based Neuro-Symbolic Approach for Pipe Severity Prediction in Sewer Networks arXiv Paper Ngoc Thai Le et al. Yesterday 004 A Structured Knowledge Infrastructure for Domain-Specific Data Asset Discovery arXiv Paper Mengdi Chen, Yuanxin Huang et al. Yesterday 005 A Systems Engineering Framework for Vision-Language-Enabled UAV Triage and Disaster Response arXiv Paper S. Saha, Bhuvan Rajanasiriyur Jagadeesha et al. Yesterday 006 A foundation model of numerical intelligence with cross-disciplinary generalization arXiv Paper Chenghan Wu et al. Yesterday 007 A report-grounded vision-language foundation model for colonoscopy from 280000 routine reports arXiv Paper Jia Yu et al. Yesterday 008 AI Literacy: An Exercise in Power-Knowledge arXiv Paper Brady D. Lund, Z. A. Teel Yesterday 009 AI and Authenticity in Islamic Research: A Critical Evaluation of Generative AI Reliability, Hallucination, and Source Fidelity in Quranic, Hadith, and Fiqh Knowledge arXiv Paper Muhammad Sajjad Akbar Yesterday 010 AISPA: User-Centric System Prompt Auditing for Large Language Model Applications arXiv Paper Xiangning Lin et al. Yesterday 011 APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems arXiv Paper Shentong Mo et al. Yesterday 012 ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance arXiv Paper Dongfu Yin, Rourou Su et al. Yesterday 013 ARES: Adaptive Reasoning-Effort Steering for PPA- and Cost-Aware RTL Optimization with LLM Agents arXiv Paper Stef Cuyckens, M. Jivanescu et al. Yesterday 014 Agentic Metaverse Services: A New As-a-Service Paradigm arXiv Paper Xiaofei Xu et al. Yesterday 015 Agentic Method for Deterministic Validation of Legacy Code Migration arXiv Paper Andras Ferenczi et al. Yesterday 016 AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach arXiv Paper Zixuan Jiang et al. Yesterday 017 Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation arXiv Paper Boning Li et al. Yesterday 018 Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration arXiv Paper Ting Gong, M. Zeng et al. Yesterday 019 Algorithms for Structured Elections under Thiele Voting Rules arXiv Paper Alexandra Lassota et al. Yesterday 020 An Empirical Study of Coordination Mode as the First-Class Citizen in From-Scratch Multi-Agent Coding arXiv Paper Yanyu Ren, Yunfeng Bai et al. Yesterday 021 An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale arXiv Paper Paulo Carvao et al. Yesterday 022 Annotating Topical Legal Insights from Case Proceedings arXiv Paper Subinay Adhikary, Dwaipayan Roy et al. Yesterday 023 Arm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation arXiv Paper Dohun Lee, Kyeonghyun Yoo et al. Yesterday 024 AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis arXiv Paper Bing Yan et al. Yesterday 025 Asymmetric Communication: Large Language Models and Language Games arXiv Paper Enzo Fenoglio Yesterday 026 AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification arXiv Paper Haobo Li, Eunseo Jung et al. Yesterday 027 Back to All-Entity Ranking: Sampler-Dependent Evaluation in Continuous-Time Dynamic Graphs arXiv Paper Minwoo Yu, Young-guk Ha Yesterday 028 Baikal: Structured Search for Deep Research over Data Lakes arXiv Paper Dhruv Agarwal, Rishitha Guttapalle Mohan et al. Yesterday 029 Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation arXiv Paper Yuhan Zhu, Mingxuan Du et al. Yesterday 030 Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures arXiv Paper Sweta Banerjee et al. Yesterday 031 Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training arXiv Paper Jiawen Tao et al. Yesterday 032 Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories arXiv Paper Zhaoji Wang, Wanyu Si et al. Yesterday 033 BlueprintRepair: Typed Local Edits for Failed Lean Proof Blueprints arXiv Paper Ruslan Khrulev Yesterday 034 CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance arXiv Paper Anubhav Lakra et al. Yesterday 035 CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising arXiv Paper Sina Heydari et al. Yesterday 036 CORE: In-Context Reconstruction for Unified Tabular Anomaly Detection arXiv Paper Yunfeng Zhao, Qingfeng Chen et al. Yesterday 037 Can AI Follow In Einstein's Footsteps? arXiv Paper M. Shalyt, Nathan Regev et al. Yesterday 038 Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game arXiv Paper Niklas Bauer et al. Yesterday 039 Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities arXiv Paper Liangjie Zhao, Jiaqing Lyu et al. Yesterday 040 Chem World: A Large-Scale Benchmark and Physics-Informed Framework for Trustworthy Chemical Property Prediction arXiv Paper Tianyou Bai et al. Yesterday 041 Class-Aware Reinforcement Learning for Counterfactual Explanation Generation arXiv Paper Muhammad Adil Saleem, S. Raza et al. Yesterday 042 Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting arXiv Paper Kuo-Chung Peng, Samuel Yen-Chi Chen et al. Yesterday 043 ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs arXiv Paper Bingchen Liu et al. Yesterday 044 Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners arXiv Paper Feng Xiong et al. Yesterday 045 Cross-Embodiment Transfer via Behavior-Aligned Representations arXiv Paper A. Sridhar, Jensen Gao et al. Yesterday 046 Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration arXiv Paper Xiangyu Yin, Jiaxu Liu et al. Yesterday 047 DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness arXiv Paper Debin Meng et al. Yesterday 048 Deep Learning for Accelerated Long-Horizon Forecasting of Multicomponent Multiphase Microstructure Evolution in High-Entropy Alloys arXiv Paper H. Razavi, N. Moelans Yesterday 049 DeepResearch Agent System arXiv Paper Yong Huang, Yuluo Huang et al. Yesterday 050 Distilling Answer Set Programming Theories from Large Language Models arXiv Paper Nelson Higuera Ruiz et al. Yesterday 051 Diversifying Personalized Research Ideation against AI-Induced Homogenization arXiv Paper Rui Xu et al. Yesterday 052 Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings arXiv Paper Mingi Kim, Yongjun Kim et al. Yesterday 053 Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks arXiv Paper Spyridon Raptis et al. Yesterday 054 DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation arXiv Paper Hongbin Zhang, Junhao Liu et al. Yesterday 055 DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation arXiv Paper Jiacheng Tao et al. Yesterday 056 Dynamic Spectral Filtering for Temporal Graph Learning: Learning Evolving Propagation Operators arXiv Paper Yang Kong Yesterday 057 EEG-EditBench: Probing Visual Information in EEG-Image Retrieval Models with Controlled Image Edits arXiv Paper Kaifan Zhang, Lihuo He et al. Yesterday 058 EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents arXiv Paper Luigi Sigillo et al. Yesterday 059 Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale arXiv Paper Yash Pandya et al. Yesterday 060 EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE arXiv Paper Zexuan Yan et al. Yesterday