{"total":33,"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":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"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":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2508.03501","title":"Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":36,"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":"2601.04171","title":"Agentic Rubrics as Contextual Verifiers for SWE Agents","created":"2026-01-07","cited_by_count":25,"area":"lr"},{"id":"2608.19098","title":"Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation","created":"2026-08-19","cited_by_count":18,"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":"2604.14820","title":"SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling","created":"2026-04-16","cited_by_count":16,"area":"lr"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2604.11037","title":"RTMC: Step-Level Credit Assignment via Rollout Trees","created":"2026-04-13","cited_by_count":12,"area":"lr"},{"id":"2603.17829","title":"CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents","created":"2026-03-18","cited_by_count":9,"area":"lr"},{"id":"2606.28436","title":"Dockerless: Environment-Free Program Verifier for Coding Agents","created":"2026-06-26","cited_by_count":9,"area":"lr"},{"id":"2508.01550","title":"RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale","created":"2025-08-03","cited_by_count":8,"area":"lr"},{"id":"2609.11042","title":"T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks","created":"2026-09-10","cited_by_count":7,"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":"2602.11210","title":"SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents","created":"2026-02-11","cited_by_count":5,"area":"lr"},{"id":"2512.16144","title":"INTELLECT-3: Technical Report","created":"2025-12-18","cited_by_count":4,"area":"lr"},{"id":"2603.01896","title":"Agentic Code Reasoning","created":"2026-03-02","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":"2606.18284","title":"Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier","created":"2026-06-10","cited_by_count":3,"area":"lr"},{"id":"2604.00824","title":"Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2607.15610","title":"Process Reward Informed Tree Rollout for Effective Multi-Turn RL","created":"2026-07-17","cited_by_count":2,"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":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2606.01080","title":"ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2609.23377","title":"One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents","created":"2026-09-20","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":"2610.14572","title":"Reward-Aligned Distillation","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}