{"total":123,"rows":[{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386,"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":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"area":"lr"},{"id":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"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":"2508.12790","title":"Reinforcement Learning with Rubric Anchors","created":"2025-08-18","cited_by_count":113,"area":"lr"},{"id":"2503.06639","title":"Reinforcement Learning with Verifiable Rewards: GRPO's Effective Loss, Dynamics, and Success Amplification","created":"2025-03-09","cited_by_count":110,"area":"lr"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99,"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":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"area":"lr"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59,"area":"lr"},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"area":"lr"},{"id":"2502.15806","title":"A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos","created":"2025-02-19","cited_by_count":43,"area":"lr"},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"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":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","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":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2601.18543","title":"GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning","created":"2026-01-26","cited_by_count":24,"area":"lr"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2502.02061","title":"Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation","created":"2025-02-04","cited_by_count":21,"area":"lr"},{"id":"2505.16186","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","created":"2025-05-22","cited_by_count":20,"area":"lr"},{"id":"2505.06538","title":"Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model","created":"2025-05-10","cited_by_count":19,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","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":"2507.12428","title":"Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models","created":"2025-07-16","cited_by_count":17,"area":"lr"},{"id":"2510.26418","title":"Chain-of-Thought Hijacking","created":"2025-10-30","cited_by_count":16,"area":"lr"},{"id":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","cited_by_count":15,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2504.09923","title":"Guiding Reasoning in Small Language Models with LLM Assistance","created":"2025-04-14","cited_by_count":14,"area":"lr"},{"id":"2504.17130","title":"Steering the CensorShip: Uncovering Representation Vectors for LLM \"Thought\" Control","created":"2025-04-23","cited_by_count":14,"area":"lr"},{"id":"2508.04039","title":"Large Reasoning Models Are Autonomous Jailbreak Agents","created":"2025-08-04","cited_by_count":13,"area":"lr"},{"id":"2603.12246","title":"Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training","created":"2026-03-12","cited_by_count":13,"area":"lr"},{"id":"2503.17882","title":"Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior","created":"2025-03-22","cited_by_count":12,"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":"2501.19180","title":"Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning","created":"2025-01-31","cited_by_count":11,"area":"lr"},{"id":"2509.24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2508.15842","title":"Lexical Hints of Accuracy in LLM Reasoning Chains","created":"2025-08-19","cited_by_count":9,"area":"lr"},{"id":"2502.12486","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2504.09421","title":"ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model","created":"2025-04-13","cited_by_count":7,"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":"2507.21652","title":"UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases","created":"2025-07-29","cited_by_count":7,"area":"lr"},{"id":"2511.05784","title":"DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning","created":"2025-11-08","cited_by_count":7,"area":"lr"},{"id":"2601.23163","title":"Probing the Trajectories of Reasoning Traces in Large Language Models","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2507.17075","title":"LoRA is All You Need for Safety Alignment of Reasoning LLMs","created":"2025-07-22","cited_by_count":6,"area":"lr"},{"id":"2508.00324","title":"R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge","created":"2025-08-01","cited_by_count":6,"area":"lr"},{"id":"2509.11629","title":"Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2510.21285","title":"When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models","created":"2025-10-24","cited_by_count":6,"area":"lr"},{"id":"2510.11570","title":"Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails","created":"2025-10-13","cited_by_count":5,"area":"lr"},{"id":"2510.13190","title":"SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","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":"2502.07985","title":"MetaSC: Test-Time Safety Specification Optimization for Language Models","created":"2025-02-11","cited_by_count":4,"area":"lr"},{"id":"2504.02725","title":"SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning","created":"2025-04-03","cited_by_count":4,"area":"lr"},{"id":"2504.21299","title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models","created":"2025-04-30","cited_by_count":4,"area":"lr"},{"id":"2508.15790","title":"KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration","created":"2025-08-12","cited_by_count":4,"area":"lr"},{"id":"2508.20151","title":"IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2509.14760","title":"Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2509.23291","title":"Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces","created":"2025-09-27","cited_by_count":4,"area":"lr"},{"id":"2603.14602","title":"PA3: Policy-Aware Agent Alignment through Chain-of-Thought","created":"2026-03-15","cited_by_count":4,"area":"lr"},{"id":"2502.08932","title":"On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigms","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2505.21784","title":"Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2506.08399","title":"SafeCoT: Improving VLM Safety with Minimal Reasoning","created":"2025-06-10","cited_by_count":3,"area":"lr"},{"id":"2507.03167","title":"Where Do Reasoning Models Refuse?","created":"2025-07-03","cited_by_count":3,"area":"lr"},{"id":"2507.20150","title":"The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models","created":"2025-07-27","cited_by_count":3,"area":"lr"},{"id":"2508.09099","title":"Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving","created":"2025-08-12","cited_by_count":3,"area":"lr"},{"id":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2510.26606","title":"Normative Reasoning in Large Language Models: A Comparative Benchmark from Logical and Modal Perspectives","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2601.08000","title":"Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety","created":"2026-01-12","cited_by_count":3,"area":"lr"},{"id":"2605.08930","title":"Internalizing Safety Understanding in Large Reasoning Models via Verification","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2606.25013","title":"Do Thinking Tokens Help with Safety?","created":"2026-06-23","cited_by_count":3,"area":"lr"},{"id":"2507.15974","title":"Does More Inference-Time Compute Really Help Robustness?","created":"2025-07-21","cited_by_count":2,"area":"lr"},{"id":"2508.18649","title":"PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2509.04501","title":"Understanding Reinforcement Learning for Model Training, and future directions with GRAPE","created":"2025-09-02","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":"2512.00412","title":"Red Teaming Large Reasoning Models","created":"2025-11-29","cited_by_count":2,"area":"lr"},{"id":"2512.01848","title":"Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2602.11549","title":"Native Reasoning Models: Training Language Models to Reason on Unverifiable Data","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2602.13562","title":"Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2602.21346","title":"Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment","created":"2026-02-24","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":"2603.17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","created":"2026-03-18","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":"2508.03054","title":"Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning","created":"2025-08-05","cited_by_count":1,"area":"lr"},{"id":"2511.09682","title":"Rebellion: Noise-Robust Reasoning Training for Audio Reasoning Models","created":"2025-11-12","cited_by_count":1,"area":"lr"},{"id":"2511.12861","title":"From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models","created":"2025-11-17","cited_by_count":1,"area":"lr"},{"id":"2512.07141","title":"Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2602.04224","title":"RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2602.06795","title":"Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2603.05618","title":"Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2604.03587","title":"SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization","created":"2026-04-04","cited_by_count":1,"area":"lr"},{"id":"2604.09665","title":"Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model","created":"2026-04-01","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}