{"total":102,"rows":[{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304,"area":"lr"},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"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":"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":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"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":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43,"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":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","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":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"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":"2504.08813","title":"SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models","created":"2025-04-09","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":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24,"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":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2502.12202","title":"To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models","created":"2025-02-16","cited_by_count":22,"area":"lr"},{"id":"2502.09673","title":"Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning","created":"2025-02-13","cited_by_count":20,"area":"lr"},{"id":"2405.20902","title":"Preemptive Answer \"Attacks\" on Chain-of-Thought Reasoning","created":"2024-05-31","cited_by_count":19,"area":"lr"},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2505.15404","title":"How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study","created":"2025-05-21","cited_by_count":18,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","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":"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":"2501.17749","title":"Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation","created":"2025-01-29","cited_by_count":13,"area":"lr"},{"id":"2508.04039","title":"Large Reasoning Models Are Autonomous Jailbreak Agents","created":"2025-08-04","cited_by_count":13,"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":"2506.10979","title":"How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?","created":"2025-06-12","cited_by_count":11,"area":"lr"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2605.15239","title":"Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation","created":"2026-05-14","cited_by_count":11,"area":"lr"},{"id":"2503.19134","title":"MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2504.16489","title":"Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate","created":"2025-04-23","cited_by_count":10,"area":"lr"},{"id":"2601.23143","title":"THINKSAFE: Self-Generated Safety Alignment for Reasoning Models","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2502.11137","title":"Safety Evaluation of DeepSeek Models in Chinese Contexts","created":"2025-02-16","cited_by_count":9,"area":"lr"},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2407.16205","title":"Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models","created":"2024-07-23","cited_by_count":8,"area":"lr"},{"id":"2505.16241","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","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":"2601.21051","title":"Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report","created":"2026-01-28","cited_by_count":7,"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":"2510.05498","title":"Prototype-Based Dynamic Steering for Large Language Models","created":"2025-10-07","cited_by_count":6,"area":"lr"},{"id":"2606.22873","title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","created":"2026-06-22","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":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2605.17329","title":"LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails","created":"2026-05-17","cited_by_count":5,"area":"lr"},{"id":"2606.09701","title":"Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2503.16529","title":"Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts","created":"2025-03-18","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":"2509.14760","title":"Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2509.24269","title":"AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2503.17365","title":"How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers","created":"2025-02-01","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":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2510.21049","title":"Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2601.14127","title":"The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning","created":"2026-01-20","cited_by_count":3,"area":"lr"},{"id":"2602.08874","title":"Do Reasoning LLMs Refuse What They Infer in Long Contexts?","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2602.11096","title":"Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away","created":"2026-02-11","cited_by_count":3,"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":"2510.17057","title":"The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2603.17368","title":"Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.00012","title":"Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2607.13394","title":"GFlowRL: Scaling Distribution-Matching RL to Large Language Models","created":"2026-07-15","cited_by_count":2,"area":"lr"},{"id":"2501.01872","title":"Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions","created":"2025-01-03","cited_by_count":1,"area":"lr"},{"id":"2509.18382","title":"Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints","created":"2025-09-22","cited_by_count":1,"area":"lr"},{"id":"2510.17759","title":"VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2510.18154","title":"Annotating the Chain-of-Thought: A Behavior-Labeled Dataset for AI Safety","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2605.05678","title":"Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.08936","title":"Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2605.27932","title":"When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.29068","title":"Robust and Efficient Guardrails with Latent Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.31073","title":"ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","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":"2606.18327","title":"Self-CTRL: Self-Consistency Training with Reinforcement Learning","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2606.26686","title":"Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation","created":"2026-06-25","cited_by_count":1,"area":"lr"},{"id":"2607.21619","title":"Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2511.21214","title":"Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models","created":"2025-11-26","cited_by_count":0,"area":"lr"},{"id":"2601.01624","title":"How Does Prefix Matter in Reasoning Model Tuning?","created":"2026-01-04","cited_by_count":0,"area":"lr"},{"id":"2602.04856","title":"CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2602.06650","title":"Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2603.21697","title":"Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models","created":"2026-03-23","cited_by_count":0,"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":"2605.19485","title":"Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2605.24497","title":"Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2605.26772","title":"Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2608.09542","title":"Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.22915","title":"Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.18471","title":"First Token Matters: Understanding Safety Collapse in Large Reasoning Models","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}