{"total":51,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2510.19363","title":"LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts","created":"2025-10-22","cited_by_count":29,"area":"lr"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2512.14051","title":"OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value","created":"2025-12-16","cited_by_count":15,"area":null},{"id":"2506.14234","title":"Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team","created":"2025-06-17","cited_by_count":13,"area":"lr"},{"id":"2512.18160","title":"Propose, Solve, Verify: Self-Play Through Formal Verification","created":"2025-12-20","cited_by_count":13,"area":"synth"},{"id":"2602.11590","title":"Learn from Your Mistakes: Self-Correcting Masked Diffusion Models","created":"2026-02-12","cited_by_count":13,"area":"diffusion"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2510.12803","title":"AutoCode: LLMs as Problem Setters for Competitive Programming","created":"2025-09-29","cited_by_count":11,"area":null},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2601.22975","title":"Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2508.05710","title":"Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning","created":"2025-08-07","cited_by_count":9,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"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":"2512.23422","title":"Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"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":"2601.09733","title":"Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2604.02721","title":"GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning","created":"2026-04-03","cited_by_count":4,"area":"agents"},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2601.12465","title":"Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping","created":"2026-01-18","cited_by_count":3,"area":"lr"},{"id":"2605.14445","title":"FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2510.06101","title":"The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models","created":"2025-10-07","cited_by_count":2,"area":"lr"},{"id":"2510.18814","title":"A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning","created":"2025-10-21","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":"2605.07248","title":"PaT: Planning-after-Trial for Efficient Test-Time Code Generation","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2510.21853","title":"Policy Optimization Prefers The Path of Least Resistance","created":"2025-10-22","cited_by_count":1,"area":"lr"},{"id":"2512.11463","title":"Motif-2-12.7B-Reasoning: A Practitioner's Guide to RL Training Recipes","created":"2025-12-11","cited_by_count":1,"area":"lr"},{"id":"2601.06953","title":"X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2604.27977","title":"D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2607.26504","title":"From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models","created":"2026-07-29","cited_by_count":1,"area":"diffusion"},{"id":"2509.14281","title":"SCoGen: Scenario-Centric Graph-Based Synthesis of Real-World Code Problems","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.06825","title":"Adaptive Tool Generation with Models as Tools and Reinforcement Learning","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2512.00127","title":"Generating Verifiable Chain of Thoughts from Exection-Traces","created":"2025-11-28","cited_by_count":0,"area":"lr"},{"id":"2605.11299","title":"Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.27971","title":"Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses","created":"2026-05-27","cited_by_count":0,"area":"diffusion"},{"id":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2609.12489","title":"Confidence-Gated Transductive Test Generation for Code Reranking","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.36864","title":"Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.12659","title":"MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.19685","title":"Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}