{"total":34,"rows":[{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"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":"2603.09786","title":"Quantifying the Necessity of Chain of Thought through Opaque Serial Depth","created":"2026-03-10","cited_by_count":8,"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":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","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":"2601.11517","title":"Do explanations generalize across large reasoning models?","created":"2026-01-16","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":"2605.29192","title":"ReasonOps: Operator Segmentation for LLM Reasoning Traces","created":"2026-05-28","cited_by_count":5,"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":"2603.26410","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":"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":"2606.20560","title":"How Transparent is DiffusionGemma?","created":"2026-06-18","cited_by_count":3,"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":"2604.06613","title":"The Detection-Extraction Gap: Models Know the Answer Before They Can Say It","created":"2026-04-08","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":"2602.01017","title":"How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic Experiments","created":"2026-02-01","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":"2604.14888","title":"Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models","created":"2026-04-16","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":"2606.23404","title":"ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models","created":"2026-06-22","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":"2608.05188","title":"Position: It's Time to Optimize LLMs for Self-Consistency","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2608.29464","title":"Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered","created":"2026-08-29","cited_by_count":1,"area":"lr"},{"id":"2602.14265","title":"STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2609.04194","title":"Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.24071","title":"Monitorable Chart Reasoning Agents via Verifiable Process Rewards","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.24243","title":"Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.33220","title":"When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.38107","title":"Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.04914","title":"Monitorability Disposition in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}