{"total":138,"rows":[{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165,"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":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26,"area":"lr"},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","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":"2510.09312","title":"Verifying Chain-of-Thought Reasoning via Its Computational Graph","created":"2025-10-10","cited_by_count":20,"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":"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":"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":"2510.23966","title":"A Pragmatic Way to Measure Chain-of-Thought Monitorability","created":"2025-10-28","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":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","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":"2602.18297","title":"Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory","created":"2026-02-20","cited_by_count":10,"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":"2510.27338","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":"2608.09867","title":"Stealing Reasoning Traces from Proprietary LLM APIs","created":"2026-08-10","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":"2603.09786","title":"Quantifying the Necessity of Chain of Thought through Opaque Serial Depth","created":"2026-03-10","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":"2604.22709","title":"Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought","created":"2026-04-24","cited_by_count":8,"area":"lr"},{"id":"2512.10931","title":"Asynchronous Reasoning: Training-Free Interactive Thinking LLMs","created":"2025-12-11","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":"2603.16928","title":"Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback","created":"2026-03-14","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":"2605.17672","title":"Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models","created":"2026-05-17","cited_by_count":7,"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":"2510.06410","title":"Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory?","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2601.05076","title":"Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models","created":"2026-01-08","cited_by_count":5,"area":"lr"},{"id":"2601.11517","title":"Do explanations generalize across large reasoning models?","created":"2026-01-16","cited_by_count":5,"area":"lr"},{"id":"2601.13368","title":"Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models","created":"2026-01-19","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":"2603.30036","title":"Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?","created":"2026-03-31","cited_by_count":5,"area":"lr"},{"id":"2605.18549","title":"Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2605.29192","title":"ReasonOps: Operator Segmentation for LLM Reasoning Traces","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2606.13603","title":"Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models","created":"2026-06-11","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":"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":"2512.01222","title":"Unsupervised decoding of encoded reasoning using language model interpretability","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2603.23607","title":"Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset","created":"2026-03-24","cited_by_count":4,"area":"lr"},{"id":"2603.26410","title":"Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models","created":"2026-03-27","cited_by_count":4,"area":"lr"},{"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":"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":"2510.10448","title":"RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation","created":"2025-10-12","cited_by_count":3,"area":"lr"},{"id":"2511.11187","title":"ReTrace: Interactive Visualizations for Reasoning Traces of Large Reasoning Models","created":"2025-11-14","cited_by_count":3,"area":"lr"},{"id":"2511.12001","title":"Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations","created":"2025-11-15","cited_by_count":3,"area":"lr"},{"id":"2601.19061","title":"Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models","created":"2026-01-27","cited_by_count":3,"area":"lr"},{"id":"2605.12460","title":"Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2605.15257","title":"Training on Documents About Monitoring Leads to CoT Obfuscation","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2606.20560","title":"How Transparent is DiffusionGemma?","created":"2026-06-18","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":"2508.11386","title":"Retrieval-augmented reasoning with lean language models","created":"2025-08-15","cited_by_count":2,"area":"lr"},{"id":"2510.11278","title":"ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models","created":"2025-10-13","cited_by_count":2,"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":"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"},{"id":"2510.22362","title":"Mapping Faithful Reasoning in Language Models","created":"2025-10-25","cited_by_count":2,"area":"lr"},{"id":"2602.13904","title":"Diagnosing Pathological Chain-of-Thought in Reasoning Models","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2604.06427","title":"The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning","created":"2026-04-07","cited_by_count":2,"area":"lr"},{"id":"2604.23460","title":"Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2605.11746","title":"When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2605.28301","title":"Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2606.29712","title":"Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2607.03502","title":"Reading Between the Dots: Decoding Hidden Computation across Filler Tokens","created":"2026-07-03","cited_by_count":2,"area":"lr"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2608.02089","title":"How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2608.04735","title":"Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2508.02789","title":"Cognitive Loop via In-Situ Optimization: Self-Adaptive Reasoning for Science","created":"2025-08-04","cited_by_count":1,"area":"lr"},{"id":"2509.06169","title":"Reasoning Language Model for Personalized Lung Cancer Screening","created":"2025-09-07","cited_by_count":1,"area":"lr"},{"id":"2509.17177","title":"FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions","created":"2025-09-21","cited_by_count":1,"area":"lr"},{"id":"2509.21465","title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","created":"2025-09-25","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":"2512.07407","title":"Training Language Models to Use Prolog as a Tool","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2601.22735","title":"MM-THEBench: Do Reasoning MLLMs Think Reasonably?","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.24210","title":"From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves","created":"2026-02-27","cited_by_count":1,"area":"lr"},{"id":"2603.12397","title":"Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors","created":"2026-03-12","cited_by_count":1,"area":"lr"},{"id":"2603.21286","title":"When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors","created":"2026-03-22","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":"2605.22870","title":"The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.27901","title":"The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.28742","title":"CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.28913","title":"Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.23404","title":"ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2606.24251","title":"Probing the Misaligned Thinking Process of Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2607.01571","title":"Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2607.09786","title":"Length Penalties Make Chain-of-Thought Less Monitorable","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2608.03291","title":"The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2608.03401","title":"Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2608.05188","title":"Position: It's Time to Optimize LLMs for Self-Consistency","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2608.18078","title":"Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions","created":"2026-05-29","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}