11 papers
Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems
Jiabao Ji, Yongchao Chen, Yang Zhang +4
Multi-robot control in cluttered environments is a challenging problem that involves complex physical constraints, including robot-robot collisions, robot-obstacle collisions, and…
Simulation to Rules: A Dual-VLM Framework for Formal Visual Planning
Yilun Hao, Yongchao Chen, Chuchu Fan +1
Vision Language Models (VLMs) show strong potential for visual planning but struggle with precise spatial and long-horizon reasoning, while Planning Domain Definition Language (PDD…
R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
Yongchao Chen, Yueying Liu, Junwei Zhou +5
Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a tex…
TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
Yongchao Chen, Jiefeng Chen, Rui Meng +6
While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guid…
AuDeRe: Automated Strategy Decision and Realization in Robot Planning and Control via LLMs
Yue Meng, Fei Chen, Yongchao Chen +1
Recent advancements in large language models (LLMs) have shown significant promise in various domains, especially robotics. However, most prior LLM-based work in robotic applicatio…
Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation
Yongchao Chen, Yilun Hao, Yang Zhang +1
Recent works have shown great potentials of Large Language Models (LLMs) in robot task and motion planning (TAMP). Current LLM approaches generate text- or code-based reasoning cha…