{"total":46,"rows":[{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249,"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":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2505.23575","title":"CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring","created":"2025-05-29","cited_by_count":54,"area":"lr"},{"id":"2506.01926","title":"Large language models can learn and generalize steganographic chain-of-thought under process supervision","created":"2025-06-02","cited_by_count":32,"area":"lr"},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2506.22777","title":"Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning","created":"2025-06-28","cited_by_count":21,"area":"lr"},{"id":"2503.00237","title":"Agentic AI Needs a Systems Theory","created":"2025-02-28","cited_by_count":19,"area":"lr"},{"id":"2506.04909","title":"When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models","created":"2025-06-05","cited_by_count":18,"area":"lr"},{"id":"2508.00943","title":"LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring","created":"2025-07-31","cited_by_count":18,"area":"lr"},{"id":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17,"area":"lr"},{"id":"2501.16513","title":"Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models","created":"2025-01-27","cited_by_count":16,"area":"lr"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"area":"lr"},{"id":"2602.18297","title":"Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory","created":"2026-02-20","cited_by_count":10,"area":"lr"},{"id":"2512.00218","title":"Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2512.11949","title":"Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors","created":"2025-12-12","cited_by_count":9,"area":"lr"},{"id":"2510.09714","title":"All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2603.28590","title":"MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models","created":"2026-03-30","cited_by_count":8,"area":"lr"},{"id":"2507.21652","title":"UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases","created":"2025-07-29","cited_by_count":7,"area":"lr"},{"id":"2603.16928","title":"Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback","created":"2026-03-14","cited_by_count":7,"area":"lr"},{"id":"2605.05835","title":"Evaluation Awareness in Language Models Has Limited Effect on Behaviour","created":"2026-05-07","cited_by_count":7,"area":"lr"},{"id":"2601.23086","title":"Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2607.22925","title":"Not All LLM Reasoning is Visible in the Chain-of-Thought","created":"2026-07-24","cited_by_count":5,"area":"lr"},{"id":"2512.01222","title":"Unsupervised decoding of encoded reasoning using language model interpretability","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2602.09147","title":"Overview of PAN 2026: Voight-Kampff Generative AI Detection, Text Watermarking, Multi-Author Writing Style Analysis, Generative Plagiarism Detection, and Reasoning Trajectory Detection","created":"2026-02-09","cited_by_count":4,"area":"lr"},{"id":"2510.01069","title":"Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning","created":"2025-10-01","cited_by_count":3,"area":"lr"},{"id":"2605.12460","title":"Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs","created":"2026-05-12","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":"2506.19492","title":"Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs","created":"2025-06-24","cited_by_count":2,"area":"lr"},{"id":"2510.19476","title":"A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2604.23460","title":"Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2604.28182","title":"Exploration Hacking: Can LLMs Learn to Resist RL Training?","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2510.09278","title":"CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2510.16340","title":"Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models","created":"2025-10-18","cited_by_count":1,"area":"lr"},{"id":"2604.22119","title":"Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework","created":"2026-04-23","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":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2608.29070","title":"Selective Disclosure of Hidden Directives in Reasoning Models: Behavioral Asymmetry and Steering","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.02302","title":"Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2610.04914","title":"Monitorability Disposition in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}