{"total":93,"rows":[{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187,"area":"diffusion"},{"id":"2505.16400","title":"AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning","created":"2025-05-22","cited_by_count":87,"area":"lr"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2509.26488","title":"dParallel: Learnable Parallel Decoding for dLLMs","created":"2025-09-30","cited_by_count":65,"area":"inference"},{"id":"2503.23157","title":"Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL","created":"2025-03-29","cited_by_count":59,"area":"lr"},{"id":"2505.21297","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","created":"2025-05-27","cited_by_count":51,"area":"lr"},{"id":"2505.19641","title":"SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond","created":"2025-05-26","cited_by_count":50,"area":"lr"},{"id":"2601.07568","title":"d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation","created":"2026-01-12","cited_by_count":37,"area":"inference"},{"id":"2505.17952","title":"Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL","created":"2025-05-23","cited_by_count":36,"area":"lr"},{"id":"2512.03759","title":"Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective","created":"2025-12-03","cited_by_count":34,"area":null},{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"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":"2508.05170","title":"ReCode: Reinforcing Code Generation with Reasoning-Process Rewards","created":"2025-08-07","cited_by_count":25,"area":"lr"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"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":"2510.15349","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-10-17","cited_by_count":17,"area":"mllm"},{"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":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2506.07851","title":"Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning","created":"2025-06-09","cited_by_count":13,"area":"inference"},{"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":"2511.01758","title":"RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks","created":"2025-11-03","cited_by_count":13,"area":"lr"},{"id":"2606.06712","title":"Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation","created":"2026-06-04","cited_by_count":11,"area":"diffusion"},{"id":"2503.15554","title":"Rethinking the Evaluation of Secure Code Generation","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2506.12278","title":"Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure","created":"2025-06-13","cited_by_count":10,"area":null},{"id":"2502.13820","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning","created":"2025-02-19","cited_by_count":9,"area":"lr"},{"id":"2605.17734","title":"Harnessing LLM Agents with Skill Programs","created":"2026-05-18","cited_by_count":9,"area":"agents"},{"id":"2603.15611","title":"Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2505.12380","title":"Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward","created":"2025-05-18","cited_by_count":7,"area":"alignment"},{"id":"2509.22824","title":"Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2510.23642","title":"VisCoder2: Building Multi-Language Visualization Coding Agents","created":"2025-10-24","cited_by_count":6,"area":"agents"},{"id":"2605.29398","title":"GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models","created":"2026-05-28","cited_by_count":6,"area":"diffusion"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2508.04865","title":"Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2509.21891","title":"AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans","created":"2025-09-26","cited_by_count":5,"area":"agents"},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2510.25528","title":"Zero Reinforcement Learning Towards General Domains","created":"2025-10-29","cited_by_count":5,"area":"lr"},{"id":"2601.03525","title":"Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation","created":"2026-01-07","cited_by_count":5,"area":"alignment"},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","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":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2606.16062","title":"Auditing Reward Hackability in Code RL Training Environments","created":"2026-06-14","cited_by_count":5,"area":null},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"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":"2602.07906","title":"AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering","created":"2026-02-08","cited_by_count":4,"area":null},{"id":"2606.06447","title":"Latent Reasoning with Normalizing Flows","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2506.03197","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2508.03333","title":"CTTS: Collective Test-Time Scaling","created":"2025-08-05","cited_by_count":3,"area":"lr"},{"id":"2509.25810","title":"Learning to Reason as Action Abstractions with Scalable Mid-Training RL","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2603.01563","title":"LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2605.13935","title":"Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models","created":"2026-05-13","cited_by_count":3,"area":"diffusion"},{"id":"2609.02987","title":"Tail-Likelihood Reinforcement Learning","created":"2026-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2508.02473","title":"NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2509.19918","title":"Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation","created":"2025-09-24","cited_by_count":2,"area":"agents"},{"id":"2511.01104","title":"HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"lr"},{"id":"2602.02143","title":"Learning Generative Selection for Best-of-N","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2602.11089","title":"DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2603.02099","title":"Recursive Think-Answer Process for LLMs and VLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2603.06065","title":"ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"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":"2603.15061","title":"Writer-R1: Enhancing Generative Writing in LLMs via Memory-augmented Replay Policy Optimization","created":"2026-03-16","cited_by_count":2,"area":"alignment"},{"id":"2604.00666","title":"TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models","created":"2026-04-01","cited_by_count":2,"area":"diffusion"},{"id":"2609.22068","title":"CodeMidas: Scaling Agentic Coding RL Environments from Code Itself","created":"2026-09-18","cited_by_count":2,"area":"agents"},{"id":"2510.00501","title":"CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2510.14828","title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2601.00575","title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs","created":"2026-01-02","cited_by_count":1,"area":null},{"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":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2604.18473","title":"Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts","created":"2026-04-20","cited_by_count":1,"area":"moe"},{"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":"2605.31058","title":"Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2506.11081","title":"SAGE:Specification-Aware Grammar Extraction for Automated Test Case Generation with LLMs","created":"2025-06-04","cited_by_count":0,"area":null},{"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":"2605.17174","title":"Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation","created":"2026-05-16","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":"2607.14735","title":"CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2607.20862","title":"CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.26457","title":"DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.24135","title":"Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2608.29798","title":"R$^2$A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment","created":"2026-08-30","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":"2609.34509","title":"Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.39859","title":"Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Models","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.03665","title":"Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models","created":"2026-10-02","cited_by_count":0,"area":"diffusion"},{"id":"2610.05373","title":"Towards Unbiased On-Policy Distillation for Block Diffusion Language Models","created":"2026-10-04","cited_by_count":0,"area":"diffusion"},{"id":"2610.18200","title":"A Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19157","title":"DivAlgo: A systematic evaluation of algorithmic diversity for code generation models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}