让智能体具备心理理论能力，能推理他人想法并协作完成任务。
BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind
- 在Minecraft中构建分层信念模拟器，支持多层心理状态推理。
- 实验验证智能体可正确识别他人错误信念并预测其行为。
- 开源工具支持大模型驱动的智能体控制方法设计与评估。
本文提出开源模拟器BeliefNest，使具身智能体在Minecraft环境中通过心理理论（Theory of Mind）执行协作任务。BeliefNest动态构建分层信念模拟器，显式表示自我与他人的嵌套信念状态，支持开放域任务中的心理推理。该系统基于各信念状态生成提示，便于设计和评估基于大语言模型（LLMs）的智能体控制方法。实验表明，智能体能够推断他人信念，并在错误信念任务中准确预测其行为。
原文摘要 · Abstract (English)
This paper introduces an open-source simulator, BeliefNest, designed to enable embodied agents to perform collaborative tasks by leveraging Theory of Mind. BeliefNest dynamically and hierarchically constructs simulators within a Minecraft environment, allowing agents to explicitly represent nested belief states about themselves and others. This enables agent control in open-domain tasks that require Theory of Mind reasoning. The simulator provides a prompt generation mechanism based on each belief state, facilitating the design and evaluation of methods for agent control utilizing large language models (LLMs). We demonstrate through experiments that agents can infer others' beliefs and predict their belief-based actions in false-belief tasks.
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。