{"total":18,"rows":[{"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":"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":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2512.10931","title":"Asynchronous Reasoning: Training-Free Interactive Thinking LLMs","created":"2025-12-11","cited_by_count":7,"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":"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":"2510.00319","title":"DecepChain: Inducing Deceptive Reasoning in Large Language Models","created":"2025-09-30","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":"2510.07697","title":"Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs","created":"2025-10-09","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":"2604.08423","title":"Synthetic Data for any Differentiable Target","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2601.13752","title":"Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2602.00707","title":"Self-Guard: Defending Large Reasoning Models via enhanced self-reflection","created":"2026-01-31","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":"2604.23488","title":"Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation","created":"2026-04-26","cited_by_count":1,"area":"lr"},{"id":"2601.03388","title":"Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models","created":"2026-01-06","cited_by_count":0,"area":"lr"},{"id":"2608.03745","title":"Risky Business: Measuring The Faithfulness-Safety Tension","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2609.05088","title":"Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?","created":"2026-09-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}