{"total":23,"rows":[{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91,"area":"lr"},{"id":"2505.14617","title":"The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"area":"lr"},{"id":"2507.20526","title":"Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition","created":"2025-07-28","cited_by_count":24,"area":"lr"},{"id":"2503.01908","title":"UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning","created":"2025-02-28","cited_by_count":21,"area":"lr"},{"id":"2505.11063","title":"Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2510.26037","title":"SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2608.10669","title":"REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems","created":"2026-08-11","cited_by_count":4,"area":"lr"},{"id":"2604.09748","title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","created":"2026-04-10","cited_by_count":3,"area":"lr"},{"id":"2606.01991","title":"SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2606.07054","title":"TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents","created":"2026-06-05","cited_by_count":3,"area":"lr"},{"id":"2509.23882","title":"Quant Fever, Reasoning Blackholes, Schrodinger's Compliance, and More: Probing GPT-OSS-20B","created":"2025-09-28","cited_by_count":1,"area":"lr"},{"id":"2605.12131","title":"Rollout Cards: A Reproducibility Standard for Agent Research","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2606.08234","title":"SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2606.21445","title":"AutoRAS: Learning Robust Agentic Systems with Primitive Representations","created":"2026-06-19","cited_by_count":1,"area":"lr"},{"id":"2604.04120","title":"Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression","created":"2026-04-05","cited_by_count":0,"area":"lr"},{"id":"2609.34537","title":"The Marathon of Scientific Reasoning: Robustness of Scientific Agents to Perturbations in Multi-Turn Interactions","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.39146","title":"MADBench: Benchmarking the Security of Multi-Agent Debate","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.03938","title":"MLLMs Fail to Refuse when Using Tools Agentically","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}