{"total":102,"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":"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":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"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":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158,"area":"lr"},{"id":"2505.23885","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation","created":"2025-05-29","cited_by_count":131,"area":"lr"},{"id":"2505.14970","title":"Self-Evolving Curriculum for LLM Reasoning","created":"2025-05-20","cited_by_count":112,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2507.14111","title":"CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning","created":"2025-07-18","cited_by_count":61,"area":"lr"},{"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":"2504.15275","title":"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning","created":"2025-04-21","cited_by_count":50,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2506.11425","title":"Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards","created":"2025-06-13","cited_by_count":42,"area":"lr"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35,"area":"lr"},{"id":"2509.19128","title":"PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation","created":"2025-09-23","cited_by_count":32,"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":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2512.21919","title":"SWE-RM: Execution-free Feedback For Software Engineering Agents","created":"2025-12-26","cited_by_count":28,"area":"lr"},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26,"area":"lr"},{"id":"2601.04171","title":"Agentic Rubrics as Contextual Verifiers for SWE Agents","created":"2026-01-07","cited_by_count":25,"area":"lr"},{"id":"2503.21961","title":"Entropy-Gated Branching for Efficient Test-Time Reasoning","created":"2025-03-27","cited_by_count":22,"area":"lr"},{"id":"2505.14625","title":"TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2505.23604","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","created":"2025-05-29","cited_by_count":17,"area":"lr"},{"id":"2509.11963","title":"ToolRM: Outcome Reward Models for Tool-Calling Large Language Models","created":"2025-09-15","cited_by_count":17,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"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":"2505.21668","title":"R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning","created":"2025-05-27","cited_by_count":15,"area":"lr"},{"id":"2510.01279","title":"TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture","created":"2025-09-30","cited_by_count":15,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2509.01684","title":"Reinforcement Learning for Machine Learning Engineering Agents","created":"2025-09-01","cited_by_count":14,"area":"lr"},{"id":"2511.14846","title":"Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization","created":"2025-11-18","cited_by_count":13,"area":"lr"},{"id":"2505.18955","title":"Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models","created":"2025-05-25","cited_by_count":12,"area":"lr"},{"id":"2505.20196","title":"Temporal Sampling for Forgotten Reasoning in LLMs","created":"2025-05-26","cited_by_count":12,"area":"lr"},{"id":"2506.16136","title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","created":"2025-06-19","cited_by_count":12,"area":"lr"},{"id":"2508.10118","title":"From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation","created":"2025-08-13","cited_by_count":12,"area":"lr"},{"id":"2607.14171","title":"Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning","created":"2026-07-15","cited_by_count":12,"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":"2601.13572","title":"Behavior Knowledge Merge in Reinforced Agentic Models","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"id":"2505.20561","title":"Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2505.20777","title":"TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs","created":"2025-05-27","cited_by_count":9,"area":"lr"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2504.01698","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","created":"2025-04-02","cited_by_count":8,"area":"lr"},{"id":"2505.12717","title":"ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving","created":"2025-05-19","cited_by_count":8,"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":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","cited_by_count":8,"area":"lr"},{"id":"2510.03632","title":"MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information","created":"2025-10-04","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":"2601.17699","title":"SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL","created":"2026-01-25","cited_by_count":7,"area":"lr"},{"id":"2605.02909","title":"Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2506.10481","title":"OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics","created":"2025-06-12","cited_by_count":6,"area":"lr"},{"id":"2508.19097","title":"Reasoning LLMs in the Medical Domain: A Literature Survey","created":"2025-08-26","cited_by_count":6,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2510.22775","title":"Scalable Supervision for Software Agents via Patch Reasoning","created":"2025-10-26","cited_by_count":5,"area":"lr"},{"id":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2602.11210","title":"SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents","created":"2026-02-11","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":"2605.11556","title":"Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers","created":"2026-05-12","cited_by_count":5,"area":"lr"},{"id":"2505.13718","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"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":"2507.17548","title":"CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning","created":"2025-07-23","cited_by_count":4,"area":"lr"},{"id":"2508.03018","title":"Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning","created":"2025-08-05","cited_by_count":4,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2608.17393","title":"LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents","created":"2026-08-18","cited_by_count":4,"area":"lr"},{"id":"2506.00845","title":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2601.23257","title":"From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2603.03680","title":"MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation","created":"2026-03-04","cited_by_count":3,"area":"lr"},{"id":"2603.20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","created":"2026-03-20","cited_by_count":3,"area":"lr"},{"id":"2604.16918","title":"Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning","created":"2026-04-18","cited_by_count":3,"area":"lr"},{"id":"2507.06013","title":"CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation","created":"2025-07-08","cited_by_count":2,"area":"lr"},{"id":"2509.07006","title":"ArGen: Auto-Regulation of Generative AI via GRPO and Policy-as-Code","created":"2025-09-06","cited_by_count":2,"area":"lr"},{"id":"2511.05874","title":"An Empirical Study of Reasoning Steps in Thinking Code LLMs","created":"2025-11-08","cited_by_count":2,"area":"lr"},{"id":"2602.11639","title":"PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2604.28182","title":"Exploration Hacking: Can LLMs Learn to Resist RL Training?","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2507.05065","title":"Replacing thinking with tool usage enables reasoning in small language models","created":"2025-07-07","cited_by_count":1,"area":"lr"},{"id":"2509.09942","title":"Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2510.07774","title":"Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards","created":"2025-10-09","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":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","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":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2602.08868","title":"AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.18334","title":"Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2606.07689","title":"Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.20908","title":"Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2608.29831","title":"A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.23808","title":"FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.25442","title":"WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.34359","title":"Improving Large Language Models for Code through Runtime Program-State Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.03361","title":"Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}