CoBel-World: Harnessing LLM Reasoning to Build a Collaborative Belief World for Optimizing Embodied Multi-Agent Collaboration

Zhimin Wang, ShaoKang He, Duo Wu, Jinghe Wang, Linjia Kang, Jing Yu, Zhi Wang

Keywords: multi-agent collaboration, LLM, Embodied AI

TL;DR: We propose a novel framework that introduces belief modeling for embodied mutli-agent collaboration to improve collaboration efficiency and reduce communication costs.

Abstract:

Effective real-world multi-agent collaboration requires not only accurate planning but also the ability to reason about collaborators' intents-a crucial capability for avoiding miscoordination and redundant communication under partial observable environments. Due to their strong planning and reasoning capabilities, large language models (LLMs) have emerged as promising autonomous agents for collaborative task solving.
However, existing collaboration frameworks for LLMs overlook their reasoning potential for $\textit{dynamic intent inference}$, and thus produce inconsistent plans and redundant communication, reducing collaboration efficiency.
To bridge this gap, we propose $\textit{\textbf{CoBel-World}}$, a novel framework that equips LLM agents with a $\textit{\textbf{co}llaborative \textbf{bel}ief world}$-an internal representation jointly modeling the physical environment and collaborators' mental states.
CoBel-World enables agents to parse open-world task knowledge into structured beliefs via a symbolic belief language, and perform zero-shot Bayesian-style belief updates through LLM reasoning. This allows agents to proactively detect potential miscoordination (e.g., conflicting plans) and communicate adaptively. Evaluated on challenging embodied benchmarks (i.e., TDW-MAT and C-WAH), CoBel-World significantly reduces communication costs by $\textbf{22-60\\%}$ and improves task completion efficiency by $\textbf{4-28\\%}$ compared to the strongest baseline. Our results show that explicit, intent-aware belief modeling is essential for efficient and human-like collaboration in LLM-based multi-agent systems.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 1060