Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| SqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability Hai Xia, Pablo Manrique, Stefan Szeider Published: 2026-10-09Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-09 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E16 / R13 (93%) | 45 |
| Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga Emilio Ferrara Published: 2026-10-09Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E10 / R11 (92%) | 45 |
| Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding Mingu Lee, Mukul Gagrani, Raghavv Goel, Risheek Garrepalli Published: 2026-10-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (95%) | - |
| SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty Mengyue Wu, Minghao Lv, Xuenan Xu, Yixuan Li Published: 2026-10-09Area: cs.AICitations: 20 Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E10 / R8 (94%) | 20 |
| SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories Chun Yong Chong, Jiajun Hu Published: 2026-10-09Area: cs.AICitations: 53 Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E8 / R6 (91%) | 53 |
| SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle Jia Li, Lin Yang, Shi-Min Hu, Xiting Liu Published: 2026-10-09Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-10-09 | cs.SE | ai-safety, csse, preprint | E17 / R12 (93%) | - |
| SwingGuard: Risk-Conditioned Multi-Agent Swing Trading with Dual-Timescale Governance Jiahua Xu, Junzhou Su, Teng Li, Yebo Feng Published: 2026-10-09Area: cs.MACitations: - Tags: ai-safety, csma, preprint | 2026-10-09 | cs.MA | ai-safety, csma, preprint | E13 / R11 (94%) | - |
| Tabular Foundation Models Are Effectively Shallow Irene Cannistraci, Julia E. Vogt Published: 2026-10-09Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-09 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (94%) | 15 |
| Task Context Shapes Component Roles in Language Models Dani S Bassett, Sovesh Mohapatra Published: 2026-10-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E12 / R6 (93%) | - |
| Teaching neural decoders with language Guoliang Li, Tzyy-Ping Jung, Xiaorong Gao, Xuan Wen Published: 2026-10-09Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E13 / R8 (93%) | 15 |
| The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs Junyi Hu, Peiyu Wang, Qiji Zhou, Yue Zhang Published: 2026-10-09Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-09 | cs.CV | ai-safety, cscv, preprint | E13 / R8 (95%) | - |
| The Limits of Manipulation within Personalized Incentive Policies Alessa Mayer, Amir Brudner, Andrea Araldo, Ravi Seshadri Published: 2026-10-09Area: cs.MACitations: - Tags: ai-safety, csma, preprint | 2026-10-09 | cs.MA | ai-safety, csma, preprint | E7 / R5 (95%) | - |
| The value of information and the emergence of communication in evolved e-puck robots Fernando Montes-Gonzalez Published: 2026-10-09Area: cs.ROCitations: 23 Tags: ai-safety, csro, preprint | 2026-10-09 | cs.RO | ai-safety, csro, preprint | E9 / R6 (93%) | 23 |
| Towards Defining, Measuring, and Leveraging Creativity in AI Applications Alexander Tuzhilin, Jingyi Yang Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E10 / R8 (96%) | - |
| Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents Fuli Feng, Lei Chen, Wentao Shi, Xierui Song Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E9 / R7 (94%) | - |
| UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes Nazar Andrushko, Vera Schmitt, Veronika Solopova Published: 2026-10-09Area: cs.AICitations: 12 Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E12 / R9 (93%) | 12 |
| Variance-Reduced Policy Gradient is Nearly Minimax-Optimal Leonardo Cesani, Marcello Restelli, Matteo Papini Published: 2026-10-09Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-10-09 | cs.LG | ai-safety, cslg, preprint | E7 / R7 (92%) | 45 |
| VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning Chaoli Wang, Chenglong Yu, Gordon Dai, Hua Shen Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E9 / R8 (92%) | - |
| VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs Chuanting Zhang, Daojun Liang, Fuqiang Wang, Hanlin Kong Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E8 / R7 (93%) | - |
| Web$hell: A Unified Interface for Agentic Web Access Deogyong Kim, Dongha Lee, Donguk Kwon, Sangam Lee Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E11 / R10 (93%) | - |
| What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training Bing Qin, Kequan Niu, Xiaocheng Feng, Yiqiao Yang Published: 2026-10-09Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (90%) | 45 |
| When AI Advisors Agree: Distinguishing Forecast Risk from Forecast Reliability Russlan Ramdowar Published: 2026-10-09Area: cs.MACitations: 8 Tags: ai-safety, csma, preprint | 2026-10-09 | cs.MA | ai-safety, csma, preprint | E8 / R6 (94%) | 8 |
| When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors Adarsh Jamadandi, Aline Roumy, Nicolas Keriven Published: 2026-10-09Area: cs.LGCitations: 53 Tags: ai-safety, cslg, preprint | 2026-10-09 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (91%) | 53 |
| When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows Chunrong Fang, Shengcheng Yu, Yuchen Ling, Zhenyu Chen Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E11 / R12 (91%) | - |
| When Generative Models Act as Simulators Michael Hobley, Pietro Perona, Sevan Brodjian Published: 2026-10-09Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-09 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (95%) | - |
| When MLLMs miss what humans read: diagnosing and learning to read squint text Chen Peng, Jianbo Huang, Linrui Qin, Mengwei Xu Published: 2026-10-09Area: cs.CVCitations: 15 Tags: ai-safety, cscv, preprint | 2026-10-09 | cs.CV | ai-safety, cscv, preprint | E10 / R10 (94%) | 15 |
| Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction Bingxuan Li, Chaoyun Zhang, Hang Yan, Hui Li Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E8 / R7 (92%) | - |
| X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems Benjamin Newman, Edoardo Debenedetti, Ivan Evtimov, Ninareh Mehrabi Published: 2026-10-09Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-09 | cs.AI | ai-safety, csai, preprint | E10 / R9 (91%) | - |
| Your Discrete Graph Diffusion Model is Secretly Memorizing Adarsh Jamadandi, Nicolas Keriven Published: 2026-10-09Area: cs.LGCitations: 36 Tags: ai-safety, cslg, preprint | 2026-10-09 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (94%) | 36 |
| A 3D Characterization Framework for Intelligent Sequential Decision Making Carolina Fortuna, Sadig Gojayev Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E12 / R10 (93%) | - |