{"total":78,"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":"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":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"area":"lr"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"id":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"id":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36,"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":"2505.14617","title":"The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness","created":"2025-05-20","cited_by_count":30,"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":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26,"area":"lr"},{"id":"2510.19851","title":"Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability","created":"2025-10-21","cited_by_count":22,"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":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","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":"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":"2502.09192","title":"Thinking beyond the anthropomorphic paradigm benefits LLM research","created":"2025-02-13","cited_by_count":14,"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":"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":"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":"2508.02833","title":"TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback","created":"2025-08-04","cited_by_count":11,"area":"lr"},{"id":"2505.16448","title":"The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models","created":"2025-05-22","cited_by_count":10,"area":"lr"},{"id":"2507.08218","title":"Simple Mechanistic Explanations for Out-Of-Context Reasoning","created":"2025-07-10","cited_by_count":10,"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":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"id":"2510.27338","title":"Reasoning Models Sometimes Output Illegible Chains of Thought","created":"2025-10-31","cited_by_count":9,"area":"lr"},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"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":"2603.22582","title":"Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?","created":"2026-03-23","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":"2505.19690","title":"Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models","created":"2025-05-26","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":"2508.06361","title":"Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts","created":"2025-08-08","cited_by_count":5,"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":"2603.20172","title":"Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation","created":"2026-03-20","cited_by_count":4,"area":"lr"},{"id":"2603.26410","title":"Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models","created":"2026-03-27","cited_by_count":4,"area":"lr"},{"id":"2507.03167","title":"Where Do Reasoning Models Refuse?","created":"2025-07-03","cited_by_count":3,"area":"lr"},{"id":"2510.00319","title":"DecepChain: Inducing Deceptive Reasoning in Large Language Models","created":"2025-09-30","cited_by_count":3,"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":"2511.09222","title":"Toward Honest Language Models for Deductive Reasoning","created":"2025-11-12","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":"2605.15257","title":"Training on Documents About Monitoring Leads to CoT Obfuscation","created":"2026-05-14","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":"2511.00379","title":"Diverse Human Value Alignment for Large Language Models via Ethical Reasoning","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2602.03994","title":"Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2603.09957","title":"Think Before You Lie: How Reasoning Leads to Honesty","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2604.06427","title":"The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning","created":"2026-04-07","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":"2605.28823","title":"What are They Thinking? Delineation, Probing, and Tracking of Concepts in LLMs","created":"2026-04-07","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":"2510.16340","title":"Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models","created":"2025-10-18","cited_by_count":1,"area":"lr"},{"id":"2512.20812","title":"Semantic Deception: When Reasoning Models Can't Compute an Addition","created":"2025-12-23","cited_by_count":1,"area":"lr"},{"id":"2603.12397","title":"Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors","created":"2026-03-12","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":"2605.16301","title":"Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2605.17958","title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2606.18327","title":"Self-CTRL: Self-Consistency Training with Reinforcement Learning","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2606.24251","title":"Probing the Misaligned Thinking Process of Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2607.08173","title":"Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets","created":"2026-07-09","cited_by_count":1,"area":"lr"},{"id":"2608.05188","title":"Position: It's Time to Optimize LLMs for Self-Consistency","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2602.17127","title":"The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI","created":"2026-02-19","cited_by_count":0,"area":"lr"},{"id":"2603.26846","title":"Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry","created":"2026-03-27","cited_by_count":0,"area":"lr"},{"id":"2605.28825","title":"MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2606.10740","title":"When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.14049","title":"Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2607.26952","title":"Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning?","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2609.31121","title":"Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.34056","title":"Steering Language Model Goals with Value Transplant","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35074","title":"When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36254","title":"Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models","created":"2026-09-28","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}