{"total":22,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.19736","title":"UserRL: Training Interactive User-Centric Agent via Reinforcement Learning","created":"2025-09-24","cited_by_count":32,"area":"agents"},{"id":"2602.03419","title":"SWE-World: Building Software Engineering Agents in Docker-Free Environments","created":"2026-02-03","cited_by_count":25,"area":"agents"},{"id":"2605.25624","title":"CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents","created":"2026-05-25","cited_by_count":23,"area":"agents"},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22,"area":"agents"},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","cited_by_count":22,"area":"agents"},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2605.22781","title":"DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback","created":"2026-05-21","cited_by_count":12,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2604.01496","title":"From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents","created":"2026-04-02","cited_by_count":6,"area":"agents"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2609.07925","title":"FrogNano: Training a 4B Coding Agent via Online Task Synthesis","created":"2026-09-07","cited_by_count":4,"area":"agents"},{"id":"2609.09133","title":"ExecCritic: Learn to Test, Test to Improve for Coding Agents","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2607.12463","title":"Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2604.07789","title":"ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents","created":"2026-04-09","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2510.05943","title":"EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models","created":"2025-10-07","cited_by_count":0,"area":"agents"},{"id":"2604.21501","title":"GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation","created":"2026-04-23","cited_by_count":0,"area":"agents"},{"id":"2609.32631","title":"SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.07898","title":"FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.12598","title":"Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}