{"total":96,"rows":[{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2505.12346","title":"SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization","created":"2025-05-18","cited_by_count":89,"area":"lr"},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75,"area":"lr"},{"id":"2603.08754","title":"Hindsight Credit Assignment for Long-Horizon LLM Agents","created":"2026-03-07","cited_by_count":65,"area":"agents"},{"id":"2506.17211","title":"BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning","created":"2025-06-20","cited_by_count":63,"area":"lr"},{"id":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52,"area":"lr"},{"id":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2506.09340","title":"RePO: Replay-Enhanced Policy Optimization","created":"2025-06-11","cited_by_count":39,"area":"lr"},{"id":"2506.09839","title":"OctoNav: Towards Generalist Embodied Navigation","created":"2025-06-11","cited_by_count":34,"area":"lr"},{"id":"2505.17017","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO","created":"2025-05-22","cited_by_count":31,"area":"lr"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2506.09016","title":"SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning","created":"2025-06-10","cited_by_count":29,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"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":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2510.01037","title":"CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs","created":"2025-10-01","cited_by_count":19,"area":"lr"},{"id":"2602.01601","title":"Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards","created":"2026-02-02","cited_by_count":17,"area":null},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2505.22914","title":"cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning","created":"2025-05-28","cited_by_count":16,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.22200","title":"EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework","created":"2025-06-27","cited_by_count":14,"area":"lr"},{"id":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2602.14338","title":"Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning","created":"2026-02-15","cited_by_count":14,"area":"lr"},{"id":"2509.23232","title":"SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts","created":"2025-09-27","cited_by_count":12,"area":"lr"},{"id":"2505.15311","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","created":"2025-05-21","cited_by_count":11,"area":"lr"},{"id":"2505.19788","title":"Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition","created":"2025-05-26","cited_by_count":11,"area":"lr"},{"id":"2603.24840","title":"Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR","created":"2026-03-25","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":"2506.07160","title":"GeometryZero: Advancing Geometry Solving via Group Contrastive Policy Optimization","created":"2025-06-08","cited_by_count":9,"area":"lr"},{"id":"2506.11480","title":"LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment","created":"2025-06-13","cited_by_count":9,"area":"lr"},{"id":"2509.21792","title":"FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2604.08865","title":"SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks","created":"2026-04-10","cited_by_count":9,"area":"lr"},{"id":"2510.04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","created":"2025-10-06","cited_by_count":8,"area":null},{"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":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","cited_by_count":7,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2606.05885","title":"When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training","created":"2026-06-04","cited_by_count":7,"area":"agents"},{"id":"2505.24584","title":"AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up","created":"2025-05-30","cited_by_count":6,"area":"agents"},{"id":"2601.22582","title":"MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning","created":"2026-01-30","cited_by_count":6,"area":"lr"},{"id":"2506.04913","title":"Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study","created":"2025-06-05","cited_by_count":5,"area":"lr"},{"id":"2506.20241","title":"Enhancing Large Language Models through Structured Reasoning","created":"2025-06-25","cited_by_count":5,"area":"lr"},{"id":"2509.24050","title":"Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"id":"2509.26306","title":"Interactive Learning for LLM Reasoning","created":"2025-09-30","cited_by_count":5,"area":"lr"},{"id":"2512.09756","title":"MOA: Multi-Objective Alignment for Role-Playing Agents","created":"2025-12-10","cited_by_count":5,"area":null},{"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":"2604.08905","title":"StaRPO: Stability-Augmented Reinforcement Policy Optimization","created":"2026-04-10","cited_by_count":5,"area":"lr"},{"id":"2605.26606","title":"Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training","created":"2026-05-26","cited_by_count":5,"area":null},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2510.07737","title":"ToolExpander: Extending the Frontiers of Tool-Using Reinforcement Learning to Weak LLMs","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2512.14944","title":"PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2602.05630","title":"Rewards as Labels: Revisiting RLVR from a Classification Perspective","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2605.06642","title":"StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2608.20492","title":"Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs","created":"2026-08-20","cited_by_count":4,"area":"lr"},{"id":"2510.15979","title":"Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2601.05002","title":"On the Hidden Objective Biases of Group-based Reinforcement Learning","created":"2026-01-08","cited_by_count":3,"area":"lr"},{"id":"2602.00815","title":"Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement","created":"2026-01-31","cited_by_count":3,"area":"lr"},{"id":"2603.18859","title":"RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2604.28005","title":"Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning","created":"2026-04-30","cited_by_count":3,"area":"lr"},{"id":"2605.10937","title":"Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping","created":"2026-05-11","cited_by_count":3,"area":"lr"},{"id":"2510.17157","title":"GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2606.05606","title":"Cross-Epoch Adaptive Rollout Optimization for RL Post-Training","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.07950","title":"The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning","created":"2026-06-06","cited_by_count":2,"area":"lr"},{"id":"2607.26253","title":"Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2505.12951","title":"DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management","created":"2025-05-19","cited_by_count":1,"area":"lr"},{"id":"2507.01752","title":"Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training","created":"2025-07-02","cited_by_count":1,"area":"safety"},{"id":"2508.05011","title":"Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation","created":"2025-08-07","cited_by_count":1,"area":"alignment"},{"id":"2509.25966","title":"MUVLA: Learning to Explore Object Navigation via Map Understanding","created":"2025-09-30","cited_by_count":1,"area":"vla"},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.22225","title":"SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG","created":"2025-12-17","cited_by_count":1,"area":"rag"},{"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":"2605.07353","title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.20865","title":"Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.25731","title":"Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.27293","title":"BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2606.03094","title":"FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.07000","title":"Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization","created":"2026-06-05","cited_by_count":1,"area":"lr"},{"id":"2506.13358","title":"Socratic RL: A Novel Framework for Efficient Knowledge Acquisition through Iterative Reflection and Viewpoint Distillation","created":"2025-06-16","cited_by_count":0,"area":"distill"},{"id":"2601.06702","title":"GRASP LoRA: GRPO Guided Adapter Sparsity Policy for Cross Lingual Transfer","created":"2026-01-10","cited_by_count":0,"area":"lr"},{"id":"2602.14169","title":"Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.29951","title":"MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2607.18470","title":"RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.05631","title":"ChronoVision: Temporal Reasoning via Latent State Reconstruction","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.17289","title":"PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2609.34990","title":"MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35082","title":"Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36932","title":"Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37111","title":"Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.03223","title":"AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.09679","title":"CERO: Where and When to Allocate Rollouts for RL Post-Training","created":"2026-10-07","cited_by_count":0,"area":"deeprl"},{"id":"2610.12161","title":"When KL Regularization Misfires in Group Policy Optimization","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16105","title":"Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}