{"total":23,"rows":[{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55,"area":"agents"},{"id":"2602.23008","title":"Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization","created":"2026-02-26","cited_by_count":19,"area":"agents"},{"id":"2509.01920","title":"Dynamic Speculative Agent Planning","created":"2025-09-02","cited_by_count":12,"area":"agents"},{"id":"2404.09248","title":"Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts","created":"2024-04-14","cited_by_count":6,"area":"agents"},{"id":"2603.05044","title":"WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents","created":"2026-03-05","cited_by_count":6,"area":"agents"},{"id":"2510.19949","title":"Surfer 2: The Next Generation of Cross-Platform Computer Use Agents","created":"2025-10-22","cited_by_count":5,"area":"agents"},{"id":"2508.21104","title":"PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning","created":"2025-08-28","cited_by_count":4,"area":"agents"},{"id":"2606.07367","title":"Self-evolving LLM agents with in-distribution Optimization","created":"2026-06-05","cited_by_count":4,"area":"agents"},{"id":"2604.27955","title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2607.05458","title":"Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning","created":"2026-07-05","cited_by_count":3,"area":"agents"},{"id":"2604.05808","title":"Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2604.19907","title":"SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2606.00708","title":"MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition","created":"2026-05-30","cited_by_count":2,"area":"agents"},{"id":"2606.03698","title":"Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2508.14751","title":"HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents","created":"2025-08-20","cited_by_count":0,"area":"agents"},{"id":"2602.17930","title":"MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2604.23557","title":"DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision Making","created":"2026-04-26","cited_by_count":0,"area":"agents"},{"id":"2607.01557","title":"DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.24779","title":"HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2608.03606","title":"Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2610.02554","title":"Test-time Multi-agent Coordination by Decomposed Value Gradient Flow","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.09294","title":"RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment","created":"2026-10-07","cited_by_count":0,"area":"agents"}],"next_cursor":null}