{"total":170,"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":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289,"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":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165,"area":"lr"},{"id":"2504.07952","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","created":"2025-04-10","cited_by_count":163,"area":null},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2506.19143","title":"Thought Anchors: Which LLM Reasoning Steps Matter?","created":"2025-06-23","cited_by_count":129,"area":"lr"},{"id":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"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":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"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":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"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":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"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":"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":"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":"2604.05655","title":"LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals","created":"2026-04-07","cited_by_count":24,"area":"lr"},{"id":"2505.13774","title":"Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models","created":"2025-05-19","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":"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":"2505.13143","title":"Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models","created":"2025-05-19","cited_by_count":20,"area":"lr"},{"id":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","cited_by_count":19,"area":null},{"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":"2510.27378","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":"2510.27484","title":"Thought Branches: Interpreting LLM Reasoning Requires Resampling","created":"2025-10-31","cited_by_count":16,"area":"lr"},{"id":"2512.23032","title":"Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization","created":"2025-12-28","cited_by_count":16,"area":"lr"},{"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":"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":"2505.22888","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":"2506.04832","title":"Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models","created":"2025-06-05","cited_by_count":14,"area":"lr"},{"id":"2504.14379","title":"The Geometry of Self-Verification in a Task-Specific Reasoning Model","created":"2025-04-19","cited_by_count":13,"area":"lr"},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2505.23945","title":"A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models","created":"2025-05-29","cited_by_count":12,"area":"lr"},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2508.16695","title":"Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?","created":"2025-08-21","cited_by_count":11,"area":"lr"},{"id":"2602.08499","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards","created":"2026-02-09","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":"2509.13316","title":"Do Activation Verbalization Methods Convey Privileged Information?","created":"2025-09-16","cited_by_count":10,"area":"mechinterp"},{"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":"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":"2508.19827","title":"Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?","created":"2025-08-27","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":"2602.01425","title":"One Probe Won't Catch Them All: Towards Targeted Deception Detection","created":"2026-02-01","cited_by_count":9,"area":"mechinterp"},{"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":"2602.10117","title":"Biases in the Blind Spot: Detecting What LLMs Fail to Mention","created":"2026-02-10","cited_by_count":8,"area":"lr"},{"id":"2507.09788","title":"TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit","created":"2025-07-13","cited_by_count":7,"area":null},{"id":"2511.08409","title":"Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs","created":"2025-11-11","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":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2512.18196","title":"LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision","created":"2025-12-20","cited_by_count":6,"area":"lr"},{"id":"2601.07663","title":"Reasoning Models Will Sometimes Lie About Their Reasoning","created":"2026-01-12","cited_by_count":6,"area":"lr"},{"id":"2601.14691","title":"Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation","created":"2026-01-21","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2603.01437","title":"Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2603.17199","title":"Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2505.11875","title":"J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2510.06410","title":"Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory?","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2511.03235","title":"From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers","created":"2025-11-05","cited_by_count":5,"area":null},{"id":"2512.12777","title":"State over Tokens: Characterizing the Role of Reasoning Tokens","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2601.22436","title":"Large Language Model Agents Are Not Always Faithful Self-Evolvers","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2605.18549","title":"Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2605.24396","title":"Understanding and Mitigating Premature Confidence for Better LLM Reasoning","created":"2026-05-23","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":"2505.13500","title":"Noise Injection Systemically Degrades Large Language Model Safety Guardrails","created":"2025-05-16","cited_by_count":4,"area":"safety"},{"id":"2506.21584","title":"Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2508.19202","title":"Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning","created":"2025-08-26","cited_by_count":4,"area":"lr"},{"id":"2508.20018","title":"SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2602.17544","title":"Evaluating Chain-of-Thought Reasoning through Reusability and Verifiability","created":"2026-02-19","cited_by_count":4,"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":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2606.12689","title":"Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models","created":"2026-06-10","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":"2508.02584","title":"MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2509.00971","title":"CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs","created":"2025-08-31","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":"2601.14553","title":"Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2605.24286","title":"Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning","created":"2026-05-22","cited_by_count":3,"area":"lr"},{"id":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2605.25603","title":"Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy","created":"2026-05-25","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":"2607.20935","title":"Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad","created":"2026-07-23","cited_by_count":3,"area":"lr"},{"id":"2607.22629","title":"Masked Distillation: Internalizing the Chain-of-Thought in Language Models","created":"2026-06-18","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":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"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"}],"next_cursor":"100"}