穷人的智能体建模：在笔记本电脑上模拟大型LLM智能体社会

AI 摘要

该论文提出一种在笔记本电脑上模拟大规模LLM智能体社会的方法，通过用低参数代理模型替代每个LLM智能体，这些代理模型从数百到数千次廉价查询中拟合而来。研究引入了一个交互顺序×记忆的分类法，用于预测替代误差的N趋势，并在EconAgent等八个LLM模拟中验证了该方法的有效性。

正文节选

Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop Abstract Replacing individual LLM agents with low-parameter surrogates fitted from cheap queries enables scalable society simulations, with validity predicted by an interaction-order and memory taxonomy. Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents N

发布时间：—

抓取时间：2026-08-13 16:11

来源机构：Hugging Face