{"total":17,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"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":"2601.03321","title":"HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize","created":"2026-01-06","cited_by_count":3,"area":"lr"},{"id":"2512.07611","title":"Comparative Analysis and Parametric Tuning of PPO, GRPO, and DAPO for LLM Reasoning Enhancement","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2605.08817","title":"How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2606.31825","title":"Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2602.04265","title":"Boosting LLM Reasoning via Human-Inspired Reward Shaping","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2602.06475","title":"Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2604.06636","title":"SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2606.15307","title":"Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes","created":"2026-06-13","cited_by_count":1,"area":"lr"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2607.00482","title":"Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2608.30632","title":"GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning","created":"2026-08-31","cited_by_count":1,"area":"lr"},{"id":"2601.14599","title":"Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective","created":"2026-01-21","cited_by_count":0,"area":"lr"},{"id":"2601.21244","title":"Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2606.08815","title":"Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2610.09804","title":"BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation","created":"2026-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}