让大模型在游戏里协作完成复杂任务，发现沟通是当前最大瓶颈。
Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
- 设计多智能体框架，让LLM在Minecraft中控制角色协作
- 实验表明沟通细节使性能下降最高达15%
- 适合研究多智能体协作与具身推理的学者
协作在日常生活中无处不在且至关重要——从交换想法、分配任务到共同制定计划。本文研究大语言模型（LLM）如何自适应协作以完成复杂的具身推理任务。为此，我们提出了MINDcraft，一个可轻松扩展的平台，支持LLM智能体在开放世界游戏Minecraft中控制角色；以及MineCollab，用于测试具身与协作推理的不同维度。实验发现，当前最先进智能体在有效协作中的主要瓶颈是高效的自然语言通信，当需要沟通详细的任务完成计划时，智能体性能最高下降15%。结论表明，现有LLM智能体在多智能体协作尤其是具身场景中仍不充分优化，亟需超越上下文学习和模仿学习的方法。项目官网：https://mindcraft-minecollab.github.io/
原文摘要 · Abstract (English)
Collaboration is ubiquitous and essential in day-to-day life -- from exchanging ideas, to delegating tasks, to generating plans together. This work studies how LLMs can adaptively collaborate to perform complex embodied reasoning tasks. To this end we introduce MINDcraft, an easily extensible platform built to enable LLM agents to control characters in the open-world game of Minecraft; and MineCollab, a benchmark to test the different dimensions of embodied and collaborative reasoning. An experimental study finds that the primary bottleneck in collaborating effectively for current state-of-the-art agents is efficient natural language communication, with agent performance dropping as much as 15% when they are required to communicate detailed task completion plans. We conclude that existing LLM agents are ill-optimized for multi-agent collaboration, especially in embodied scenarios, and highlight the need to employ methods beyond in-context and imitation learning. Our website can be found here: https://mindcraft-minecollab.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。