{"total":75,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79,"area":"agents"},{"id":"2508.17445","title":"TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling","created":"2025-08-24","cited_by_count":61,"area":"lr"},{"id":"2506.05183","title":"TreeRPO: Tree Relative Policy Optimization","created":"2025-06-05","cited_by_count":46,"area":"lr"},{"id":"2507.02841","title":"StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason","created":"2025-07-03","cited_by_count":39,"area":"lr"},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2604.09459","title":"From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models","created":"2026-04-10","cited_by_count":23,"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":"2605.11853","title":"GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation","created":"2026-05-12","cited_by_count":12,"area":"lr"},{"id":"2511.02303","title":"Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation","created":"2025-11-04","cited_by_count":11,"area":"lr"},{"id":"2604.10701","title":"Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning","created":"2026-04-12","cited_by_count":11,"area":null},{"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":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"id":"2606.11119","title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","created":"2026-06-09","cited_by_count":10,"area":"agents"},{"id":"2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","created":"2025-11-29","cited_by_count":9,"area":"lr"},{"id":"2509.15110","title":"TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference","created":"2025-09-18","cited_by_count":8,"area":"alignment"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"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":"2603.02216","title":"ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue","created":"2026-02-10","cited_by_count":8,"area":null},{"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":"2604.18401","title":"CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities","created":"2026-04-20","cited_by_count":8,"area":"agents"},{"id":"2605.19436","title":"CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2601.05688","title":"SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More","created":"2026-01-09","cited_by_count":7,"area":"lr"},{"id":"2602.09331","title":"Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2604.20659","title":"GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning","created":"2026-04-22","cited_by_count":5,"area":"lr"},{"id":"2508.04460","title":"From \"Aha Moments\" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control","created":"2025-08-06","cited_by_count":4,"area":"lr"},{"id":"2510.03253","title":"Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents","created":"2025-09-26","cited_by_count":4,"area":"agents"},{"id":"2602.10231","title":"Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2605.02545","title":"Strategy-Aware Optimization Modeling with Reasoning LLMs","created":"2026-05-04","cited_by_count":4,"area":"lr"},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2605.21851","title":"OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2605.25507","title":"Credit Assignment with Resets in Language Model Reasoning","created":"2026-05-25","cited_by_count":4,"area":"lr"},{"id":"2606.12384","title":"APPO: Agentic Procedural Policy Optimization","created":"2026-06-10","cited_by_count":4,"area":"agents"},{"id":"2604.13491","title":"FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2605.27788","title":"Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2606.10507","title":"HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning","created":"2026-06-09","cited_by_count":3,"area":"agents"},{"id":"2606.18954","title":"GraphPO: Graph-based Policy Optimization for Reasoning Models","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2607.25308","title":"CAST: Game Solvers as Turn-Level Teachers for LLM Agents","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2510.09535","title":"Mitigating Overthinking through Reasoning Shaping","created":"2025-10-10","cited_by_count":2,"area":"lr"},{"id":"2510.15502","title":"The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling","created":"2025-10-17","cited_by_count":2,"area":"lr"},{"id":"2601.19404","title":"RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization","created":"2026-01-27","cited_by_count":2,"area":"lr"},{"id":"2601.20649","title":"P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2603.09551","title":"GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2604.00860","title":"Policy Improvement Reinforcement Learning","created":"2026-04-01","cited_by_count":2,"area":"deeprl"},{"id":"2605.25443","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2609.18708","title":"Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening","created":"2026-09-16","cited_by_count":2,"area":"lr"},{"id":"2510.10609","title":"OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment","created":"2025-10-12","cited_by_count":1,"area":"alignment"},{"id":"2601.08403","title":"Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2602.22697","title":"Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue","created":"2026-02-26","cited_by_count":1,"area":"agents"},{"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":"2605.01327","title":"Segment-Aligned Policy Optimization for Multi-Modal Reasoning","created":"2026-05-02","cited_by_count":1,"area":"lr"},{"id":"2606.03089","title":"Constitutional On-Policy Safe Distillation","created":"2026-06-02","cited_by_count":1,"area":"distill"},{"id":"2606.06475","title":"RREDCoT: Segment-Level Reward Redistribution for Reasoning Models","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2607.16205","title":"It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2608.06663","title":"The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2608.17499","title":"Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2609.07072","title":"Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2603.06138","title":"Partial Policy Gradients for RL in LLMs","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2605.28109","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.08346","title":"CATPO: Critique-Augmented Tree Policy Optimization","created":"2026-06-06","cited_by_count":0,"area":"lr"},{"id":"2606.09871","title":"SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.17735","title":"Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2606.22570","title":"What are Key Factors for Updates in RL for LLM Reasoning?","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2608.02951","title":"SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling","created":"2026-08-03","cited_by_count":0,"area":"alignment"},{"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":"2609.15471","title":"HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived Segments","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.32340","title":"SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33781","title":"Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.36178","title":"Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37825","title":"Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.39247","title":"Trust the Critic More","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39402","title":"Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.40035","title":"OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00838","title":"SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}