{"total":150,"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":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"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":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84,"area":"lr"},{"id":"2504.09696","title":"GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models","created":"2025-04-13","cited_by_count":82,"area":"lr"},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79,"area":"agents"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"area":"lr"},{"id":"2512.03043","title":"OneThinker: All-in-one Reasoning Model for Image and Video","created":"2025-12-02","cited_by_count":56,"area":"lr"},{"id":"2506.04207","title":"Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning","created":"2025-06-04","cited_by_count":53,"area":"lr"},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"area":"lr"},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41,"area":"lr"},{"id":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"id":"2606.16993","title":"DreamX-World 1.0: A General-Purpose Interactive World Model","created":"2026-06-15","cited_by_count":40,"area":"wm"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2508.12880","title":"Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models","created":"2025-08-18","cited_by_count":36,"area":"diffusion"},{"id":"2509.01944","title":"AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving","created":"2025-09-02","cited_by_count":34,"area":"vla"},{"id":"2505.18830","title":"On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization","created":"2025-05-24","cited_by_count":31,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2505.17508","title":"On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning","created":"2025-05-23","cited_by_count":30,"area":"lr"},{"id":"2602.09856","title":"Code2World: A GUI World Model via Renderable Code Generation","created":"2026-02-10","cited_by_count":29,"area":"wm"},{"id":"2505.14810","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","created":"2025-05-20","cited_by_count":28,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26,"area":"mllm"},{"id":"2510.04996","title":"Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives","created":"2025-10-06","cited_by_count":25,"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":"2604.15840","title":"CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution","created":"2026-04-17","cited_by_count":23,"area":"agents"},{"id":"2504.10358","title":"FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos","created":"2025-04-14","cited_by_count":22,"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":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2508.05612","title":"Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle","created":"2025-08-07","cited_by_count":19,"area":"lr"},{"id":"2601.20614","title":"Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation","created":"2026-01-28","cited_by_count":19,"area":"lr"},{"id":"2505.19866","title":"HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation","created":"2025-05-26","cited_by_count":18,"area":"lr"},{"id":"2512.24146","title":"Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning","created":"2025-12-30","cited_by_count":18,"area":"diffusion"},{"id":"2603.22212","title":"Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models","created":"2026-03-23","cited_by_count":18,"area":"wm"},{"id":"2605.28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","created":"2026-05-27","cited_by_count":17,"area":"lr"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2506.08011","title":"Play to Generalize: Learning to Reason Through Game Play","created":"2025-06-09","cited_by_count":16,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2601.20354","title":"Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models","created":"2026-01-28","cited_by_count":16,"area":null},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2602.21172","title":"NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning","created":"2026-02-24","cited_by_count":15,"area":"lr"},{"id":"2602.19208","title":"How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization","created":"2026-02-22","cited_by_count":14,"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":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2608.01964","title":"LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks","created":"2026-08-03","cited_by_count":13,"area":"agents"},{"id":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2505.12504","title":"CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models","created":"2025-05-18","cited_by_count":11,"area":"lr"},{"id":"2508.02833","title":"TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback","created":"2025-08-04","cited_by_count":11,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2509.25454","title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2604.09349","title":"Visually-Guided Policy Optimization for Multimodal Reasoning","created":"2026-04-10","cited_by_count":11,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","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":"2505.17652","title":"Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective","created":"2025-05-23","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":"2601.05432","title":"Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization","created":"2026-01-08","cited_by_count":9,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2506.18631","title":"ReDit: Reward Dithering for Improved LLM Policy Optimization","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2509.23129","title":"C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning","created":"2025-09-27","cited_by_count":8,"area":"lr"},{"id":"2509.26313","title":"One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient","created":"2025-09-30","cited_by_count":8,"area":null},{"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":"2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2602.11499","title":"What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2604.11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","created":"2026-04-13","cited_by_count":8,"area":"lr"},{"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":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2505.14403","title":"Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","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":"2602.21628","title":"RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2604.01591","title":"ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement","created":"2026-04-02","cited_by_count":5,"area":"lr"},{"id":"2507.00721","title":"UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2509.02522","title":"Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR","created":"2025-09-02","cited_by_count":4,"area":"lr"},{"id":"2510.26020","title":"PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2512.24271","title":"Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation","created":"2025-12-30","cited_by_count":4,"area":"mllm"},{"id":"2601.03661","title":"AMIR-GRPO: Inducing Implicit Preference Signals into GRPO","created":"2026-01-07","cited_by_count":4,"area":"lr"},{"id":"2601.23058","title":"From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning","created":"2026-01-30","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":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2605.12004","title":"Learning Agentic Policy from Action Guidance","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2606.10917","title":"Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution","created":"2026-06-09","cited_by_count":4,"area":"agents"},{"id":"2606.12384","title":"APPO: Agentic Procedural Policy Optimization","created":"2026-06-10","cited_by_count":4,"area":"agents"},{"id":"2608.24747","title":"SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents","created":"2026-08-25","cited_by_count":4,"area":"lr"},{"id":"2505.14264","title":"AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin","created":"2025-05-20","cited_by_count":3,"area":"lr"},{"id":"2505.17086","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","created":"2025-05-20","cited_by_count":3,"area":"rag"},{"id":"2508.16677","title":"Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration","created":"2025-08-21","cited_by_count":3,"area":"lr"},{"id":"2509.17380","title":"Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2510.09369","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2512.05962","title":"Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity","created":"2025-12-05","cited_by_count":3,"area":"lr"}],"next_cursor":"100"}