{"total":29,"rows":[{"id":"2411.02337","title":"WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning","created":"2024-11-04","cited_by_count":256,"area":"agents"},{"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":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197,"area":"agents"},{"id":"2412.13501","title":"GUI Agents: A Survey","created":"2024-12-18","cited_by_count":103,"area":"agents"},{"id":"2510.14545","title":"Agentic Entropy-Balanced Policy Optimization","created":"2025-10-16","cited_by_count":40,"area":"agents"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2502.15760","title":"Digi-Q: Learning Q-Value Functions for Training Device-Control Agents","created":"2025-02-13","cited_by_count":20,"area":"agents"},{"id":"2509.14257","title":"Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs","created":"2025-09-12","cited_by_count":14,"area":"agents"},{"id":"2606.22995","title":"Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning","created":"2026-06-22","cited_by_count":13,"area":"agents"},{"id":"2606.29502","title":"UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation","created":"2026-06-28","cited_by_count":12,"area":"agents"},{"id":"2603.19685","title":"A Subgoal-driven Framework for Improving Long-Horizon LLM Agents","created":"2026-03-20","cited_by_count":11,"area":"agents"},{"id":"2505.19428","title":"Frictional Agent Alignment Framework: Slow Down and Don't Break Things","created":"2025-05-26","cited_by_count":10,"area":"agents"},{"id":"2509.05882","title":"Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes","created":"2025-09-07","cited_by_count":7,"area":"agents"},{"id":"2604.07277","title":"Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions","created":"2026-04-08","cited_by_count":6,"area":"agents"},{"id":"2604.07960","title":"TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning","created":"2026-04-09","cited_by_count":6,"area":"agents"},{"id":"2506.17697","title":"Beyond Syntax: Action Semantics Learning for App Agents","created":"2025-06-21","cited_by_count":3,"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":"2607.04242","title":"Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning","created":"2026-07-05","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":"2603.07148","title":"Agentic Planning with Reasoning for Image Styling via Offline RL","created":"2026-03-07","cited_by_count":1,"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":"2510.13195","title":"Emotional Cognitive Modeling Framework with Desire-Driven Objective Optimization for LLM-empowered Agent in Social Simulation","created":"2025-10-15","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":"2604.10968","title":"YIELD: A Large-Scale Dataset and Evaluation Framework for Information Elicitation Agents","created":"2026-04-13","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":"2608.27672","title":"First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.35084","title":"GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents","created":"2026-09-28","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"}],"next_cursor":null}