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 |
|---|---|---|---|---|---|
| Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents Baihang Liu, Qixu Liu, Xiangyi Zeng, Xutong Wang Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E18 / R12 (92%) | 15 |
| VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails Bhavana Dalvi Mishra, Duy Nguyen, Krishnamurthy Dj Dvijotham, Lesly Miculicich Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E9 / R9 (93%) | - |
| Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems Aadit Sengupta, Pratinav Seth, Saisab Sadhu, Vinay kumar Sankarapu Published: 2026-10-08Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E9 / R5 (94%) | 45 |
| What Output-Only Review Cannot Verify: Study Contracts for Research Agents Ben Glocker, Eitan Waks Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R8 (93%) | - |
| What to Admit and How to Present: Governing Persistent Memory in LLM Agents Chang Liu, Deliang Ding Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E17 / R11 (95%) | 15 |
| When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees Fabian Denoodt, Sibylle Hess Published: 2026-10-08Area: cs.AICitations: 13 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E7 / R5 (94%) | 13 |
| When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction Ge Qu, Jack Williams, Jinyang Li, Nan Huo Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E11 / R9 (92%) | - |
| When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization Baihua He, Harrison Bo Hua Zhu, Huihang Liu, Li Zeng Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R7 (91%) | - |
| When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation Guanting Dong, Jiejun Tan, Ji-Rong Wen, Pengjun Xie Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R9 (94%) | - |
| Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding Pan Zhou, Shijing Hu, Xuancheng Ren, Zhihui Lu Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E7 / R6 (94%) | - |
| Where to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention Deyu Meng, Jun Shu, Qi Xie, Zhiqiang Pang Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E3 / R5 (91%) | - |
| Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents Bing Zhu, Guanghui Wang, Peiyang He, Wei Qiu Published: 2026-10-08Area: cs.AICitations: 48 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E8 / R7 (93%) | 48 |
| Why machines will still not rule the world Barry Smith, Jobst Landgrebe Published: 2026-10-08Area: cs.AICitations: 26 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E11 / R8 (94%) | 26 |
| Workerville: Towards an Organizational Behavior Account of Agent Safety Hanan Salam, Hanjun Luo, Haobo Zhang, Junting Mao Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E12 / R10 (94%) | - |
| Writing for the Reviewer: Defensive Writing in GPT Models Junchi Liao Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E7 / R6 (92%) | - |
| Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming Ángel Sánchez-Fernández, Diego Crespo-Pereira, Javier Pernas-Álvarez Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E11 / R7 (96%) | - |
| AgentTime: Can Agents Estimate and Control Their Own Runtime? Maksym Andriushchenko, Michael Ofengenden Published: 2026-10-07Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E10 / R8 (94%) | 15 |
| AgentTime: Can Agents Estimate and Control Their Own Runtime? Maksym Andriushchenko, Michael Ofengenden Published: 2026-10-07Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E10 / R9 (94%) | 15 |
| AI Safety Considerations for Agents With Limited Time to Act Jack Richings, Leo Zeitler, Victoria Nockles Published: 2026-10-07Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E10 / R7 (95%) | 15 |
| A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty Quantifiers Evgenia Ilia, Wilker Aziz Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-07 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E12 / R10 (94%) | - |
| Automatically Building and Updating a Knowledge Graph of MLIP Models Alexis Beer, Liudmyla Klochko, Mathieu d'Aquin Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E9 / R7 (92%) | - |
| Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models Alexander Bukharin, Ashish Vaswani, Bryan Catanzaro, Hyunwoo Kim Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E9 / R7 (94%) | - |
| Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving Adrián Zámečník, Jan Grebík, Martin Balko, Martin Koutecký Published: 2026-10-07Area: cs.AICitations: 14 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E14 / R11 (91%) | 14 |
| Cognitive Schemas, Laws and Tasks András Telcs, Antal Jakovác Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E9 / R7 (94%) | - |
| Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification Baishakhi Ray, Dongdong She, Mark Paul Santolucito, Nikolaus Holzer Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E15 / R13 (92%) | - |
| Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback Tiancheng Zhao, Yuning Yang, Zexuan Liu Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E7 / R6 (89%) | - |
| Distillation for Incrimination and Distillation for Capabilities Alek Westover, Jacqueline Tay, Sebastian Prasanna Published: 2026-10-07Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E9 / R7 (92%) | 15 |
| DrugTargetWorld: A Synthetic Biobank for Training and Benchmarking AI Scientists Alan Huang, Atman Shah, Ben Viggiano, Bruna Gomes Published: 2026-10-07Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E8 / R6 (91%) | 45 |
| Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study Chen Yang, Chunlong Zhang, Feifei Zhou, Fuqing Zhou Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E8 / R6 (95%) | - |
| DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis Hang Ni, Hao Liu, Weijia Zhang, Yizhi Song Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E8 / R7 (93%) | - |