{"total":45,"rows":[{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2506.06122","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","created":"2025-06-06","cited_by_count":101,"area":"lr"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2505.19914","title":"Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles","created":"2025-05-26","cited_by_count":56,"area":"lr"},{"id":"2505.10446","title":"Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models","created":"2025-05-15","cited_by_count":54,"area":"lr"},{"id":"2503.19633","title":"1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training","created":"2025-03-25","cited_by_count":49,"area":"lr"},{"id":"2505.24183","title":"QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation","created":"2025-05-30","cited_by_count":35,"area":"lr"},{"id":"2509.21009","title":"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training","created":"2025-09-25","cited_by_count":35,"area":"lr"},{"id":"2510.08554","title":"Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization","created":"2025-10-09","cited_by_count":33,"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":"2505.14464","title":"Not All Correct Answers Are Equal: Why Your Distillation Source Matters","created":"2025-05-20","cited_by_count":25,"area":"lr"},{"id":"2507.09075","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","created":"2025-07-11","cited_by_count":25,"area":"lr"},{"id":"2504.17565","title":"DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training","created":"2025-04-24","cited_by_count":18,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"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":"2504.14560","title":"ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model","created":"2025-04-20","cited_by_count":12,"area":"lr"},{"id":"2507.14683","title":"MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization","created":"2025-07-19","cited_by_count":12,"area":"lr"},{"id":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2510.16476","title":"NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems","created":"2025-10-18","cited_by_count":11,"area":"lr"},{"id":"2510.04081","title":"Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2509.19894","title":"PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning","created":"2025-09-24","cited_by_count":9,"area":"lr"},{"id":"2509.22824","title":"Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning","created":"2025-09-26","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":"2603.11226","title":"ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning","created":"2026-03-11","cited_by_count":6,"area":"lr"},{"id":"2511.07833","title":"MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation","created":"2025-11-11","cited_by_count":5,"area":"lr"},{"id":"2601.22642","title":"Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5,"area":"lr"},{"id":"2606.06447","title":"Latent Reasoning with Normalizing Flows","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2606.08501","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2605.22939","title":"Learnability-Informed Fine-Tuning of Diffusion Language Models","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2607.15200","title":"Mask-Aware Policy Gradients for Diffusion Language Models","created":"2026-07-16","cited_by_count":3,"area":"lr"},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2603.07777","title":"Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2603.07779","title":"Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2505.02142","title":"Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study","created":"2025-05-04","cited_by_count":1,"area":"lr"},{"id":"2604.03587","title":"SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization","created":"2026-04-04","cited_by_count":1,"area":"lr"},{"id":"2605.02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.16342","title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2608.02026","title":"HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2605.06755","title":"Gradient Extrapolation-Based Policy Optimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2606.07006","title":"RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.07748","title":"Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation","created":"2026-07-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}