{"total":14,"rows":[{"id":"2602.17025","title":"WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning","created":"2026-02-19","cited_by_count":12,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2601.02170","title":"Streaming Hallucination Detection in Long Chain-of-Thought Reasoning","created":"2026-01-05","cited_by_count":5,"area":"lr"},{"id":"2606.02020","title":"Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning","created":"2026-06-01","cited_by_count":4,"area":"lr"},{"id":"2603.00296","title":"Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2604.04500","title":"Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward","created":"2026-04-06","cited_by_count":2,"area":"lr"},{"id":"2605.11169","title":"OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2605.25524","title":"ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2608.29988","title":"AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning","created":"2026-08-30","cited_by_count":2,"area":"lr"},{"id":"2603.22754","title":"PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation","created":"2026-03-24","cited_by_count":1,"area":"lr"},{"id":"2605.12995","title":"F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2512.14332","title":"Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring","created":"2025-12-16","cited_by_count":0,"area":"lr"},{"id":"2604.21057","title":"TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2607.09698","title":"Interpreting Latent CoT Reasoning as Dynamical Systems","created":"2026-06-20","cited_by_count":0,"area":"lr"}],"next_cursor":null}