{"total":16,"rows":[{"id":"2603.05488","title":"Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought","created":"2026-03-05","cited_by_count":40,"area":"lr"},{"id":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"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":"2601.10825","title":"Reasoning Models Generate Societies of Thought","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2509.06608","title":"Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors","created":"2025-09-08","cited_by_count":8,"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":"2512.23988","title":"Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process","created":"2025-12-30","cited_by_count":5,"area":"lr"},{"id":"2511.06739","title":"Rank-1 LoRAs Encode Interpretable Reasoning Signals","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2605.16874","title":"Reasoning Can Be Restored by Correcting a Few Decision Tokens","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2602.20904","title":"Transcoder Adapters for Reasoning-Model Diffing","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2602.04843","title":"Fluid Reasoning Representations","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2605.23074","title":"PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.00726","title":"Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2607.18532","title":"Reasoning Fine-Tuning Induces Persistent Latent Policy States","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2609.00925","title":"Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2610.14270","title":"The Thinking Leakage in Reinforcement Learning for LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}