假设心智：面向多智能体任务的大语言模型心智理论脚手架构建
Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models
AI总结：
针对多智能体强化学习的非平稳性与在线自适应难题，提出搭载心智理论模块的Hypothetical Minds智能体，通过生成、评估并迭代优化他者策略假设提升规划能力，在Melting Pot基准多类任务上性能优于现有基线。
摘要：
多智能体强化学习（MARL）方法难以应对多智能体系统的非平稳性，且在与新型智能体测试时无法自适应地在线学习。本文中，我们利用大语言模型（LLM）构建了一个可应对这些挑战的自主智能体。我们的智能体Hypothetical Minds（假设心智）采用受认知科学启发的架构，具备感知、记忆模块，以及覆盖两层抽象层级的分层规划组件。我们提出了心智理论模块，该模块通过用自然语言生成关于其他智能体策略的假设，为高层规划过程搭建脚手架。它随后通过强化那些能正确预测其他智能体行为的假设，来评估并迭代优化这些假设。在Melting Pot基准的一系列竞争、混合动机及协作领域（包括双人环境和基于群体的环境）中，Hypothetical Minds的性能显著优于此前的LLM智能体基线和强化学习基线。此外，与LLM智能体基线的对比及消融实验表明，假设评估与优化对在复杂场景中取得成功至关重要。
英文摘要：
Multi-agent reinforcement learning (MARL) methods struggle with the non-stationarity of multi-agent systems and fail to adaptively learn online when tested with novel agents. Here, we leverage large language models (LLMs) to create an autonomous agent that can handle these challenges. Our agent, Hypothetical Minds, consists of a cognitively-inspired architecture, featuring modular components for perception, memory, and hierarchical planning over two levels of abstraction. We introduce the Theory of Mind module that scaffolds the high-level planning process by generating hypotheses about other agents' strategies in natural language. It then evaluates and iteratively refines these hypotheses by reinforcing hypotheses that make correct predictions about the other agents' behavior. Hypothetical Minds significantly improves performance over previous LLM-agent and RL baselines on a range of competitive, mixed motive, and collaborative domains in the Melting Pot benchmark, including both dyadic and population-based environments. Additionally, comparisons against LLM-agent baselines and ablations reveal the importance of hypothesis evaluation and refinement for succeeding on complex scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
