{"total":19,"rows":[{"id":"2506.19143","title":"Thought Anchors: Which LLM Reasoning Steps Matter?","created":"2025-06-23","cited_by_count":129,"area":"lr"},{"id":"2607.05184","title":"Rethinking On-Policy Self-Distillation for Thinking Models","created":"2026-07-06","cited_by_count":39,"area":"lr"},{"id":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2606.22600","title":"On the Position Bias of On-Policy Distillation","created":"2026-06-21","cited_by_count":26,"area":"lr"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"area":"lr"},{"id":"2510.27484","title":"Thought Branches: Interpreting LLM Reasoning Requires Resampling","created":"2025-10-31","cited_by_count":16,"area":"lr"},{"id":"2501.09775","title":"Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong","created":"2025-01-16","cited_by_count":11,"area":"lr"},{"id":"2511.04527","title":"Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics","created":"2025-11-06","cited_by_count":11,"area":"lr"},{"id":"2602.02103","title":"How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2608.19611","title":"Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation","created":"2026-08-20","cited_by_count":1,"area":"lr"},{"id":"2609.03436","title":"It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2510.13850","title":"Revisiting the UID Hypothesis in LLM Reasoning Traces","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2602.02427","title":"Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2606.08470","title":"LUNA-AD: Lightweight Uncertainty-Aware Language Model with Lifelong Learning for Autonomous Driving","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2608.29188","title":"Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2610.04933","title":"DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.15412","title":"From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.16598","title":"Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.19561","title":"REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}