{"total":18,"rows":[{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118,"area":"lr"},{"id":"2406.19392","title":"ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos","created":"2024-06-27","cited_by_count":51,"area":"lr"},{"id":"2410.08328","title":"Agents Thinking Fast and Slow: A Talker-Reasoner Architecture","created":"2024-10-10","cited_by_count":36,"area":"lr"},{"id":"2502.11433","title":"FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2503.16965","title":"Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning","created":"2025-03-21","cited_by_count":9,"area":"lr"},{"id":"2506.21230","title":"World-aware Planning Narratives Enhance Large Vision-Language Model Planner","created":"2025-06-26","cited_by_count":9,"area":"lr"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2508.01943","title":"ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks","created":"2025-08-03","cited_by_count":6,"area":"lr"},{"id":"2502.03450","title":"Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System","created":"2025-02-05","cited_by_count":5,"area":"lr"},{"id":"2506.01301","title":"Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner","created":"2025-06-02","cited_by_count":5,"area":"lr"},{"id":"2401.06603","title":"Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Planning Case Study","created":"2024-01-12","cited_by_count":3,"area":"lr"},{"id":"2505.03181","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","created":"2025-05-06","cited_by_count":3,"area":"lr"},{"id":"2509.08500","title":"TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2605.12620","title":"Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2512.15933","title":"City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs","created":"2025-12-17","cited_by_count":1,"area":"lr"},{"id":"2502.19500","title":"Conversational Planning for Personal Plans","created":"2025-02-26","cited_by_count":0,"area":"lr"},{"id":"2604.19839","title":"Environmental Understanding Vision-Language Model for Embodied Agent","created":"2026-04-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}