{"total":33,"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":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54,"area":"lr"},{"id":"2512.08153","title":"TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models","created":"2025-12-09","cited_by_count":31,"area":"lr"},{"id":"2509.18314","title":"Exploiting Tree Structure for Credit Assignment in RL Training of LLMs","created":"2025-09-22","cited_by_count":27,"area":"lr"},{"id":"2510.06672","title":"XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2509.26628","title":"Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models","created":"2025-09-30","cited_by_count":13,"area":"lr"},{"id":"2509.09284","title":"Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning","created":"2025-09-11","cited_by_count":12,"area":"lr"},{"id":"2510.24832","title":"Scheduling Your LLM Reinforcement Learning with Reasoning Trees","created":"2025-10-28","cited_by_count":12,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2512.07733","title":"SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery","created":"2025-12-08","cited_by_count":11,"area":"lr"},{"id":"2509.21154","title":"GRPO is Secretly a Process Reward Model","created":"2025-09-25","cited_by_count":10,"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":"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":"2512.00743","title":"Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards","created":"2025-11-30","cited_by_count":8,"area":"lr"},{"id":"2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2604.07165","title":"Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization","created":"2026-04-08","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":"2606.09348","title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment","created":"2026-06-08","cited_by_count":6,"area":"lr"},{"id":"2602.23802","title":"EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":5,"area":"lr"},{"id":"2601.03661","title":"AMIR-GRPO: Inducing Implicit Preference Signals into GRPO","created":"2026-01-07","cited_by_count":4,"area":"lr"},{"id":"2605.30451","title":"VeriGate: Verifier-Gated Step-Level Supervision for GRPO","created":"2026-05-28","cited_by_count":4,"area":"lr"},{"id":"2602.19049","title":"IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning","created":"2026-02-22","cited_by_count":3,"area":"lr"},{"id":"2606.18954","title":"GraphPO: Graph-based Policy Optimization for Reasoning Models","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2601.08274","title":"Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees","created":"2026-01-13","cited_by_count":2,"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":"2602.08533","title":"Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO","created":"2026-02-09","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":"2608.18682","title":"RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training","created":"2026-08-19","cited_by_count":1,"area":"lr"},{"id":"2510.25065","title":"Rewarding Structural Conformance of Reasoning using Process Mining","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2604.17328","title":"Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2608.30395","title":"When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.11061","title":"Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2609.39220","title":"Learning Process Rewards via Reasoning State Propagation","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}