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

2025-09-26

AI Summary

Existing LLM-based multi-agent frameworks lack explicit modeling of dynamic intentions, leading to plan conflicts and communication redundancy. This work proposes the Collaborative Belief World (CBW) framework, which jointly models environmental state and peer intentions in partially observable, embodied settings, enabling zero-shot, Bayesian-style structured belief updates via LLMs. CBW is the first framework to unify symbolic belief languages, explicit intention reasoning, and adaptive communication mechanisms, supporting autonomous, human-like collaborative decision-making. Evaluated on the TDW-MAT and C-WAH benchmarks, CBW reduces communication cost by 22%–60% and improves task completion efficiency by 4%–28% over the strongest baselines. These results empirically validate the critical role of intention-aware belief modeling in achieving efficient multi-agent collaboration.

Technology Category

• Multiagent Systems: Agent Communication
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

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 dynamic intent inference, and thus produce inconsistent plans and redundant communication, reducing collaboration efficiency. To bridge this gap, we propose CoBel-World, a novel framework that equips LLM agents with a collaborative belief 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 22-60% and improves task completion efficiency by 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.

Problem

• Optimizing multi-agent collaboration under partial observability
• Reducing redundant communication in LLM-based agent systems
• Improving intent inference for consistent planning coordination

Innovation

• Collaborative belief world modeling environment and mental states
• Symbolic belief language parsing open-world task knowledge
• Zero-shot Bayesian-style belief updates through LLM reasoning