# Collaborative Belief Reasoning with LLMs for Efficient Multi-Agent Collaboration

arXiv: https://arxiv.org/abs/2509.21981 · HTML: https://mlsanity.com/paper/2509.21981/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 17 of its 46 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation](https://mlsanity.com/paper/2007.04954/) (2020)
- [Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration](https://mlsanity.com/paper/2010.09890/) (2020)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://mlsanity.com/paper/2403.12482/) (2024)
- [Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1901.09207/) (2019)
- [Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models](https://mlsanity.com/paper/2310.19619/) (2023)
- [From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium](https://mlsanity.com/paper/2506.08292/) (2025)
- [Neural Recursive Belief States in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.02274/) (2021)
- [E-PDDL: A Standardized Way of Defining Epistemic Planning Problems](https://mlsanity.com/paper/2107.08739/) (2021)
- [Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/2504.08417/) (2025)

## Abstract (arXiv)

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 external open-world knowledge into structured beliefs via a symbolic belief representation module, 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 64-79% 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.