{"total":415,"rows":[{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302,"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":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2505.15879","title":"GRIT: Teaching MLLMs to Think with Images","created":"2025-05-21","cited_by_count":125,"area":"lr"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2505.16782","title":"Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning","created":"2025-05-22","cited_by_count":78,"area":"lr"},{"id":"2506.15740","title":"SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents","created":"2025-06-17","cited_by_count":71,"area":"agents"},{"id":"2509.07980","title":"Parallel-R1: Towards Parallel Thinking via Reinforcement Learning","created":"2025-09-09","cited_by_count":61,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2508.02087","title":"When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models","created":"2025-08-04","cited_by_count":50,"area":null},{"id":"2508.01191","title":"Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens","created":"2025-08-02","cited_by_count":43,"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":"2506.02536","title":"Answer Convergence as a Signal for Early Stopping in Reasoning","created":"2025-06-03","cited_by_count":40,"area":"lr"},{"id":"2603.05488","title":"Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought","created":"2026-03-05","cited_by_count":40,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2505.12886","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","created":"2025-05-19","cited_by_count":34,"area":"lr"},{"id":"2511.09149","title":"Enabling Agents to Communicate Entirely in Latent Space","created":"2025-11-12","cited_by_count":34,"area":"agents"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2605.02964","title":"Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use","created":"2026-05-03","cited_by_count":31,"area":"agents"},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2602.15785","title":"This human study did not involve human subjects: Validating LLM simulations as behavioral evidence","created":"2026-02-17","cited_by_count":29,"area":null},{"id":"2511.01805","title":"Accumulating Context Changes the Beliefs of Language Models","created":"2025-11-03","cited_by_count":28,"area":null},{"id":"2510.01367","title":"Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort","created":"2025-10-01","cited_by_count":27,"area":"lr"},{"id":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","cited_by_count":26,"area":"lr"},{"id":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2509.19284","title":"What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT","created":"2025-09-23","cited_by_count":25,"area":"lr"},{"id":"2510.16380","title":"MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes","created":"2025-10-18","cited_by_count":23,"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":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"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":"2507.14293","title":"WebGuard: Building a Generalizable Guardrail for Web Agents","created":"2025-07-18","cited_by_count":21,"area":"agents"},{"id":"2601.01984","title":"Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation","created":"2026-01-05","cited_by_count":21,"area":"lr"},{"id":"2505.17407","title":"Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2510.09312","title":"Verifying Chain-of-Thought Reasoning via Its Computational Graph","created":"2025-10-10","cited_by_count":20,"area":"lr"},{"id":"2605.19943","title":"Probabilistic Tiny Recursive Model","created":"2026-05-19","cited_by_count":19,"area":null},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2505.22017","title":"The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models","created":"2025-05-28","cited_by_count":18,"area":"lr"},{"id":"2506.13351","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2505.07735","title":"Assessing the Chemical Intelligence of Large Language Models","created":"2025-05-12","cited_by_count":17,"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":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17,"area":"lr"},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2603.07084","title":"Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR","created":"2026-03-07","cited_by_count":17,"area":"alignment"},{"id":"2509.09396","title":"LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations","created":"2025-09-11","cited_by_count":16,"area":"synth"},{"id":"2509.10723","title":"Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight","created":"2025-09-12","cited_by_count":16,"area":"agents"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2603.09906","title":"Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs","created":"2026-03-10","cited_by_count":16,"area":"lr"},{"id":"2507.19218","title":"Technological folie \\`a deux: Feedback Loops Between AI Chatbots and Mental Illness","created":"2025-07-25","cited_by_count":15,"area":null},{"id":"2509.26072","title":"The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2510.24941","title":"Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought","created":"2025-10-28","cited_by_count":15,"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":"2505.22888","title":"When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy","created":"2025-05-28","cited_by_count":14,"area":"lr"},{"id":"2602.08235","title":"When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents","created":"2026-02-09","cited_by_count":14,"area":"agents"},{"id":"2603.04069","title":"Monitoring Emergent Reward Hacking During Generation via Internal Activations","created":"2026-03-04","cited_by_count":14,"area":"alignment"},{"id":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","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":"2511.11584","title":"Output Supervision Can Obfuscate the Chain of Thought","created":"2025-10-11","cited_by_count":13,"area":"lr"},{"id":"2509.21361","title":"Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs","created":"2025-09-21","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":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2506.12241","title":"Privacy Reasoning in Ambiguous Contexts","created":"2025-06-13","cited_by_count":11,"area":"lr"},{"id":"2509.05378","title":"Code Like Humans: A Multi-Agent Solution for Medical Coding","created":"2025-09-04","cited_by_count":11,"area":"agents"},{"id":"2602.12506","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","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":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2507.15886","title":"Combining Cost-Constrained Runtime Monitors for AI Safety","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2509.24156","title":"Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models","created":"2025-09-29","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":"2506.23678","title":"Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models","created":"2025-06-30","cited_by_count":9,"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":"2510.10494","title":"Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning","created":"2025-10-12","cited_by_count":9,"area":"lr"},{"id":"2510.11196","title":"Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations","created":"2025-10-13","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":"2604.04902","title":"Are Latent Reasoning Models Easily Interpretable?","created":"2026-04-06","cited_by_count":9,"area":"lr"},{"id":"2606.15127","title":"Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation","created":"2026-06-13","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":"2601.10242","title":"Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?","created":"2026-01-15","cited_by_count":8,"area":null},{"id":"2603.16643","title":"Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy","created":"2026-03-17","cited_by_count":8,"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":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","cited_by_count":7,"area":"lr"},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"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":"2603.05167","title":"C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning","created":"2026-03-05","cited_by_count":7,"area":"lr"},{"id":"2603.10011","title":"Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2603.21396","title":"Mechanisms of Introspective Awareness","created":"2026-03-22","cited_by_count":7,"area":"mechinterp"},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2607.14552","title":"Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models","created":"2026-07-16","cited_by_count":7,"area":"lr"},{"id":"2505.12151","title":"Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features","created":"2025-05-17","cited_by_count":6,"area":"lr"},{"id":"2507.01368","title":"Activation Reward Models for Few-Shot Model Alignment","created":"2025-07-02","cited_by_count":6,"area":"mllm"},{"id":"2508.05928","title":"Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting","created":"2025-08-08","cited_by_count":6,"area":"lr"},{"id":"2508.16213","title":"MedOmni-45{\\deg}: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2508.16599","title":"Humans Perceive Wrong Narratives from AI Reasoning Texts","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2509.05739","title":"Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated","created":"2025-09-06","cited_by_count":6,"area":"lr"},{"id":"2509.23676","title":"From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models","created":"2025-09-28","cited_by_count":6,"area":"lr"}],"next_cursor":"100"}