{"total":42,"rows":[{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2410.11287","title":"Process Reward Model with Q-Value Rankings","created":"2024-10-15","cited_by_count":80,"area":"lr"},{"id":"2502.19613","title":"Self-rewarding correction for mathematical reasoning","created":"2025-02-26","cited_by_count":70,"area":"lr"},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2505.16984","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","created":"2025-05-22","cited_by_count":59,"area":"lr"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"2412.11006","title":"Entropy-Regularized Process Reward Model","created":"2024-12-15","cited_by_count":38,"area":"lr"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2505.02391","title":"Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL","created":"2025-05-05","cited_by_count":24,"area":"lr"},{"id":"2502.10581","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective","created":"2025-02-14","cited_by_count":17,"area":"lr"},{"id":"2505.23363","title":"Discriminative Policy Optimization for Token-Level Reward Models","created":"2025-05-29","cited_by_count":16,"area":"lr"},{"id":"2504.05782","title":"MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models","created":"2025-04-08","cited_by_count":15,"area":"lr"},{"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":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","cited_by_count":11,"area":"lr"},{"id":"2501.18858","title":"BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning","created":"2025-01-31","cited_by_count":10,"area":"lr"},{"id":"2503.12123","title":"MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling","created":"2025-03-15","cited_by_count":10,"area":"lr"},{"id":"2502.11656","title":"Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL","created":"2025-02-17","cited_by_count":9,"area":"lr"},{"id":"2502.13173","title":"Thinking Preference Optimization","created":"2025-02-17","cited_by_count":8,"area":"lr"},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2505.19501","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","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":"2503.23913","title":"Entropy-Based Adaptive Weighting for Self-Training","created":"2025-03-31","cited_by_count":5,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2601.10348","title":"Training-Trajectory-Aware Token Selection","created":"2026-01-15","cited_by_count":4,"area":"lr"},{"id":"2604.14646","title":"Targeted Exploration via Unified Entropy Control for Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2605.07660","title":"Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2505.11141","title":"Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2602.07832","title":"rePIRL: Learn PRM with Inverse RL for LLM Reasoning","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.29871","title":"ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"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":"2606.03937","title":"Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2511.01213","title":"Thought-For-Food: Reasoning Chain Induced Food Visual Question Answering","created":"2025-11-03","cited_by_count":0,"area":"lr"},{"id":"2603.27482","title":"Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"id":"2604.17884","title":"SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2605.24005","title":"LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition","created":"2026-05-19","cited_by_count":0,"area":"lr"}],"next_cursor":null}