關於基於代理的模型中代理能力的限制

On the limits of agency in agent-based models

September 14, 2024

作者: Ayush Chopra, Shashank Kumar, Nurullah Giray-Kuru, Ramesh Raskar, Arnau Quera-Bofarull

cs.AI

摘要

基於代理的建模（ABM）旨在通過模擬一組在環境內行動和互動的代理來理解複雜系統的行為。其實用性需要捕捉逼真的環境動態和適應性代理行為，同時高效地模擬百萬規模的人口。大型語言模型（LLMs）的最新進展為通過將LLMs作為代理來增強ABMs提供了機會，進一步捕捉適應性行為。然而，由於使用LLMs模擬大規模人口的計算不可行性，阻礙了它們的廣泛應用。在本文中，我們介紹AgentTorch——一個將ABMs擴展到數百萬代理並使用LLMs捕捉高分辨率代理行為的框架。我們對LLMs作為ABM代理的效用進行基準測試，探索模擬規模和個體代理之間的權衡。以COVID-19大流行作為案例研究，我們演示了AgentTorch如何模擬代表紐約市的840萬代理，捕捉孤立和就業行為對健康和經濟結果的影響。我們比較了基於啟發式和LLM代理的不同代理架構在預測疾病波和失業率方面的性能。此外，我們展示了AgentTorch在回顧、反事實和前瞻性分析方面的能力，突出了適應性代理行為如何幫助克服歷史數據在政策設計中的局限性。AgentTorch是一個開源項目，正在全球用於政策制定和科學發現。該框架可在此處找到：github.com/AgentTorch/AgentTorch。

English

Agent-based modeling (ABM) seeks to understand the behavior of complex systems by simulating a collection of agents that act and interact within an environment. Their practical utility requires capturing realistic environment dynamics and adaptive agent behavior while efficiently simulating million-size populations. Recent advancements in large language models (LLMs) present an opportunity to enhance ABMs by using LLMs as agents with further potential to capture adaptive behavior. However, the computational infeasibility of using LLMs for large populations has hindered their widespread adoption. In this paper, we introduce AgentTorch -- a framework that scales ABMs to millions of agents while capturing high-resolution agent behavior using LLMs. We benchmark the utility of LLMs as ABM agents, exploring the trade-off between simulation scale and individual agency. Using the COVID-19 pandemic as a case study, we demonstrate how AgentTorch can simulate 8.4 million agents representing New York City, capturing the impact of isolation and employment behavior on health and economic outcomes. We compare the performance of different agent architectures based on heuristic and LLM agents in predicting disease waves and unemployment rates. Furthermore, we showcase AgentTorch's capabilities for retrospective, counterfactual, and prospective analyses, highlighting how adaptive agent behavior can help overcome the limitations of historical data in policy design. AgentTorch is an open-source project actively being used for policy-making and scientific discovery around the world. The framework is available here: github.com/AgentTorch/AgentTorch.