{"total":122,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"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":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59,"area":"lr"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2504.09946","title":"Assessing Judging Bias in Large Reasoning Models: An Empirical Study","created":"2025-04-14","cited_by_count":30,"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":"2504.08813","title":"SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models","created":"2025-04-09","cited_by_count":29,"area":"lr"},{"id":"2506.15674","title":"Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers","created":"2025-06-18","cited_by_count":28,"area":"lr"},{"id":"2505.15400","title":"When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning","created":"2025-05-21","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":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2503.17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities","created":"2025-03-23","cited_by_count":20,"area":"lr"},{"id":"2506.05346","title":"Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets","created":"2025-06-05","cited_by_count":20,"area":"alignment"},{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19,"area":"alignment"},{"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":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2509.21651","title":"Can AI Perceive Physical Danger and Intervene?","created":"2025-09-25","cited_by_count":14,"area":null},{"id":"2510.00938","title":"Large Reasoning Models Learn Better Alignment from Flawed Thinking","created":"2025-10-01","cited_by_count":13,"area":"lr"},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2509.24296","title":"DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models","created":"2025-09-29","cited_by_count":12,"area":"safety"},{"id":"2511.12982","title":"SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization","created":"2025-11-17","cited_by_count":12,"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":"2512.11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","created":"2025-12-12","cited_by_count":11,"area":"alignment"},{"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":"2601.23143","title":"THINKSAFE: Self-Generated Safety Alignment for Reasoning Models","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2505.17244","title":"ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models","created":"2025-05-22","cited_by_count":9,"area":"lr"},{"id":"2510.17017","title":"SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents","created":"2025-10-19","cited_by_count":9,"area":"agents"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2606.23075","title":"Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies","created":"2026-06-22","cited_by_count":8,"area":"agents"},{"id":"2505.12625","title":"R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model","created":"2025-05-19","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":"2512.02306","title":"OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning","created":"2025-12-02","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":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","cited_by_count":6,"area":"alignment"},{"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":"2601.18292","title":"TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment","created":"2026-01-26","cited_by_count":6,"area":"alignment"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5,"area":"alignment"},{"id":"2512.23260","title":"Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"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":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"id":"2511.20994","title":"GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2512.23573","title":"ProGuard: Towards Proactive Multimodal Safeguard","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2606.02530","title":"SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment","created":"2026-06-01","cited_by_count":4,"area":"alignment"},{"id":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2510.18082","title":"Provably Optimal Reinforcement Learning under Safety Filtering","created":"2025-10-20","cited_by_count":3,"area":"deeprl"},{"id":"2511.21050","title":"Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs","created":"2025-11-26","cited_by_count":3,"area":"alignment"},{"id":"2512.20164","title":"AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2601.03537","title":"STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2601.03662","title":"How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2601.19231","title":"LLMs Can Unlearn Refusal with Only 1,000 Benign Samples","created":"2026-01-27","cited_by_count":3,"area":"alignment"},{"id":"2602.02136","title":"Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2602.02545","title":"Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization","created":"2026-01-30","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":"2605.08930","title":"Internalizing Safety Understanding in Large Reasoning Models via Verification","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2512.00412","title":"Red Teaming Large Reasoning Models","created":"2025-11-29","cited_by_count":2,"area":"lr"},{"id":"2601.04716","title":"Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes","created":"2026-01-08","cited_by_count":2,"area":"agents"},{"id":"2602.00861","title":"Multi-Head Attention Is a Multi-Player Game","created":"2026-01-31","cited_by_count":2,"area":null},{"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":"2602.16835","title":"NeST: Neuron Selective Tuning for LLM Safety","created":"2026-02-18","cited_by_count":2,"area":"alignment"},{"id":"2603.17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2508.08855","title":"BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2512.03704","title":"Overcoming State Inertia: Minimally Invasive Temporal Alignment for Evolving Contexts","created":"2025-12-03","cited_by_count":1,"area":"alignment"},{"id":"2603.00047","title":"What Is the Alignment Tax?","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.02225","title":"Scaling Reward Modeling without Human Supervision","created":"2026-02-11","cited_by_count":1,"area":"alignment"},{"id":"2603.02229","title":"Safety Training May Persist Through Helpfulness Optimization in LLM Agents","created":"2026-02-13","cited_by_count":1,"area":"agents"},{"id":"2603.15417","title":"Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2604.04231","title":"Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization","created":"2026-04-05","cited_by_count":1,"area":"safety"},{"id":"2604.11120","title":"Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.18946","title":"Reasoning Structure Matters for Safety Alignment of Reasoning Models","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":"2606.03089","title":"Constitutional On-Policy Safe Distillation","created":"2026-06-02","cited_by_count":1,"area":"distill"},{"id":"2606.06519","title":"SafeGene: Reusable Adapters for Transferable Safety Alignment","created":"2026-06-02","cited_by_count":1,"area":"alignment"},{"id":"2606.08451","title":"Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models","created":"2026-06-07","cited_by_count":1,"area":"alignment"},{"id":"2606.18656","title":"The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.25442","title":"PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models","created":"2026-06-24","cited_by_count":1,"area":"alignment"},{"id":"2506.10020","title":"From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment","created":"2025-06-07","cited_by_count":0,"area":"alignment"},{"id":"2508.12897","title":"RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models","created":"2025-08-18","cited_by_count":0,"area":"lr"},{"id":"2508.13246","title":"Involuntary Jailbreak: On Self-Prompting Attacks","created":"2025-08-18","cited_by_count":0,"area":"safety"},{"id":"2510.04196","title":"COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability","created":"2025-10-05","cited_by_count":0,"area":"lr"},{"id":"2510.09004","title":"Decoupling Safety into Orthogonal Subspace: Cost-Efficient and Performance-Preserving Alignment for Large Language Models","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2601.13288","title":"A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.18998","title":"Malicious Repurposing of Open Science Artefacts by Using Large Language Models","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.01528","title":"Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.02027","title":"Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"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":"2602.17546","title":"Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.01784","title":"Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2604.10990","title":"When Verification Fails: How Compositionally Infeasible Claims Escape Rejection","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.15725","title":"Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.17691","title":"SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models","created":"2026-04-20","cited_by_count":0,"area":"alignment"},{"id":"2605.03720","title":"Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2605.16471","title":"From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI","created":"2026-05-15","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}