arXiv cs.CY· Patrick Zhao, Yuxuan Li, Hirokazu Shirado·· 13 小时前AI 评分31
Model Capacity Frontier：面向 LLM 支持的社会模拟的开发框架
Model Capacity Frontier: A Development Framework for LLM-Supported Social Simulation
AI 导读
研究者提出 Model Capacity Frontier（MCF）框架，用于刻画指定架构在其可行配置范围内可达到的经验性能，并在多目标设定下用估计的 Pareto 前沿表示。该框架在约 12,000 个智能体的大学毕典人群模拟中验证：初步集成 LLM 改善了流动方向，但降低了时间占用与空间分布表现；随后对 LLM 层的架构改进提升了时间占用并恢复空间表现，同时保留了流动方向上的大部分增益。
正文 · 原文
Abstract:Large language model (LLM) agents are increasingly incorporated into agent-based models (ABMs) on the premise that richer, context-sensitive human behavior can improve empirical fidelity. However, LLM-supported ABMs introduce an open-ended design space in which subtle modeling and configuration choices, such as prompt design and environment coupling, can substantially alter outcomes. Developing LLM-supported ABMs to simulate human collective behavior therefore requires navigating configuration sensitivity while identifying the limitations of the current model architecture. In this paper, we introduce the Model Capacity Frontier (MCF), a framework that characterizes the empirical performance attainable by a specified architecture across its admissible configurations. In multi-objective settings, this capacity is represented by an estimated Pareto frontier obtained through systematic configuration exploration. We demonstrate MCF in crowd simulation of university commencement events with approximately 12,000 agents, using empirical movement data on temporal occupancy, spatial distribution, and flow direction. We first characterize the capacity of a conventional crowd model and then evaluate successive LLM-supported architectural extensions. In the process, MCF reveals which dimensions of attainable performance expand and which remain limited, providing empirical targets for refinement and re-evaluation. Initial LLM integration improves flow direction but degrades temporal occupancy and spatial distribution; subsequent architectural refinement of the LLM layer improves temporal occupancy and recovers spatial performance, while retaining much of the earlier gain in flow direction. Our case study shows how MCF guides the systematic architectural development of LLM-supported ABMs in configuration-sensitive, open-ended design spaces.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.24168 [cs.MA] |
| (or arXiv:2610.24168v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.24168 arXiv-issued DOI via DataCite |
Submission history
From: Patrick Zhao [view email]
[v1]
Fri, 16 Oct 2026 19:45:06 UTC (10,564 KB)
[v2]
Tue, 20 Oct 2026 21:58:48 UTC (10,564 KB)
来源：arXiv cs.CY · arxiv.org