{"total":18,"rows":[{"id":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2512.04220","title":"On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement","created":"2025-12-03","cited_by_count":15,"area":"lr"},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","cited_by_count":12,"area":"lr"},{"id":"2510.23049","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","created":"2025-10-27","cited_by_count":11,"area":"lr"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2601.15625","title":"Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors","created":"2026-01-22","cited_by_count":10,"area":"lr"},{"id":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2604.11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","created":"2026-04-13","cited_by_count":8,"area":"lr"},{"id":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2511.14258","title":"Entropy-Guided Reasoning Compression","created":"2025-11-18","cited_by_count":3,"area":"lr"},{"id":"2606.19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2609.20807","title":"Score Centering Stabilizes Off-policy Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"lr"},{"id":"2509.19893","title":"Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2603.07598","title":"SCA: Segment-Wise CoT Compression with Answer Alignment","created":"2026-03-08","cited_by_count":1,"area":"lr"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2609.39321","title":"GRPO Training Dynamics for Small Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}