{"total":17,"rows":[{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2407.00993","title":"Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents","created":"2024-07-01","cited_by_count":56,"area":"agents"},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46,"area":"agents"},{"id":"2607.07508","title":"Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning","created":"2026-07-08","cited_by_count":37,"area":"agents"},{"id":"2510.11345","title":"Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony","created":"2025-10-13","cited_by_count":15,"area":"agents"},{"id":"2307.09423","title":"Scaling Laws for Imitation Learning in Single-Agent Games","created":"2023-07-18","cited_by_count":11,"area":"agents"},{"id":"2311.05596","title":"LLM Augmented Hierarchical Agents","created":"2023-11-09","cited_by_count":9,"area":"agents"},{"id":"2503.13356","title":"Agents Play Thousands of 3D Video Games","created":"2025-03-17","cited_by_count":9,"area":"agents"},{"id":"2511.11828","title":"Conformal Constrained Policy Optimization for Cost-Effective LLM Agents","created":"2025-11-14","cited_by_count":7,"area":"agents"},{"id":"2510.00023","title":"ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools","created":"2025-09-24","cited_by_count":2,"area":"agents"},{"id":"2603.10098","title":"Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models","created":"2026-03-10","cited_by_count":2,"area":"agents"},{"id":"2506.05577","title":"Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems","created":"2025-06-05","cited_by_count":1,"area":"agents"},{"id":"2605.15207","title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","created":"2026-05-01","cited_by_count":1,"area":"agents"},{"id":"2609.03383","title":"TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2603.18788","title":"Mi:dm K 2.5 Pro","created":"2026-03-19","cited_by_count":0,"area":"agents"},{"id":"2610.04196","title":"Asynchronous Is Nearly Free for Evolution Strategies on Long-Horizon Agentic Tasks","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.05935","title":"ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}