TinyTroupe：一个基于LLM的多智能体人物模拟工具包
TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit
AI总结：
针对现有LLM多智能体系统在细粒度人物模拟方面的不足，提出TinyTroupe工具包，支持详细人物定义和程序化控制，用于行为研究和社会模拟。
摘要：
近期大型语言模型（LLM）的进展催生了一类新的自主智能体，重新激发并扩展了该领域的兴趣。基于LLM的多智能体系统（MAS）因此涌现，既用于辅助也用于模拟目的，但用于现实人类行为模拟的工具——及其独特的挑战和机遇——仍不成熟。现有的MAS库和工具缺乏细粒度的人物规范、群体采样设施、实验支持以及集成验证等关键能力，限制了它们在行为研究、社会模拟及相关应用中的实用性。为解决这些不足，本文介绍了TinyTroupe，一个模拟工具包，支持详细的人物定义（如国籍、年龄、职业、个性、信念、行为）并通过众多LLM驱动的机制实现程序化控制。这使得能够简洁地表述实际感兴趣的行为问题，无论是个人还是群体层面，并提供了有效的解决方案。通过代表性工作示例（如头脑风暴和市场调研会议）展示了TinyTroupe的组件，同时阐明了其目的并证明了其实用性。还提供了选定方面的定量和定性评估，包括以真实人类行为作为对照的初步实验。结果突出了可能性、局限性和权衡。该方法虽然以特定的Python实现形式呈现，但旨在作为一种新颖的概念贡献，可以部分或完全融入其他环境中。该库以开源形式提供，网址为https://github.com/microsoft/TinyTroupe。
英文摘要：
Recent advances in Large Language Models (LLM) have led to a new class of autonomous agents, renewing and expanding interest in the area. LLM-powered Multiagent Systems (MAS) have thus emerged, both for assistive and simulation purposes, yet tools for realistic human behavior simulation -- with its distinctive challenges and opportunities -- remain underdeveloped. Existing MAS libraries and tools lack fine-grained persona specifications, population sampling facilities, experimentation support, and integrated validation, among other key capabilities, limiting their utility for behavioral studies, social simulation, and related applications. To address these deficiencies, in this work we introduce TinyTroupe, a simulation toolkit enabling detailed persona definitions (e.g., nationality, age, occupation, personality, beliefs, behaviors) and programmatic control via numerous LLM-driven mechanisms. This allows for the concise formulation of behavioral problems of practical interest, either at the individual or group level, and provides effective means for their solution. TinyTroupe's components are presented using representative working examples, such as brainstorming and market research sessions, thereby simultaneously clarifying their purpose and demonstrating their usefulness. Quantitative and qualitative evaluations of selected aspects are also provided, including preliminary experiments with real human behavior as control. Results highlight possibilities, limitations, and trade-offs. The approach, though realized as a specific Python implementation, is meant as a novel conceptual contribution, which can be partially or fully incorporated in other contexts. The library is available as open source at https://github.com/microsoft/tinytroupe.
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。
