{"total":16,"rows":[{"id":"2509.22047","title":"MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems","created":"2025-09-26","cited_by_count":23,"area":"lr"},{"id":"2509.24494","title":"Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2512.06337","title":"DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization","created":"2025-12-06","cited_by_count":9,"area":"lr"},{"id":"2602.15620","title":"STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2602.20722","title":"Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2602.11455","title":"Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2605.00380","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","created":"2026-05-01","cited_by_count":6,"area":"lr"},{"id":"2601.23135","title":"Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.06453","title":"On the Plasticity and Stability for Post-Training Large Language Models","created":"2026-02-06","cited_by_count":4,"area":"lr"},{"id":"2602.04380","title":"Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2608.17423","title":"Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome Groups","created":"2026-08-18","cited_by_count":2,"area":"lr"},{"id":"2603.18756","title":"Are complicated loss functions necessary for teaching LLMs to reason?","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2605.12058","title":"Holder Policy Optimisation","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.25511","title":"CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.03234","title":"Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2607.03126","title":"ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate","created":"2026-07-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}