Reimagining Agent-based Modeling with Large Language Model Agents via Shachi
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909833632940032 |
|---|---|
| author | Kuroki, So Tian, Yingtao Misaki, Kou Ikegami, Takashi Akiba, Takuya Tang, Yujin |
| author_facet | Kuroki, So Tian, Yingtao Misaki, Kou Ikegami, Takashi Akiba, Takuya Tang, Yujin |
| contents | The study of emergent behaviors in large language model (LLM)-driven multi-agent systems is a critical research challenge, yet progress is limited by a lack of principled methodologies for controlled experimentation. To address this, we introduce Shachi, a formal methodology and modular framework that decomposes an agent's policy into core cognitive components: Configuration for intrinsic traits, Memory for contextual persistence, and Tools for expanded capabilities, all orchestrated by an LLM reasoning engine. This principled architecture moves beyond brittle, ad-hoc agent designs and enables the systematic analysis of how specific architectural choices influence collective behavior. We validate our methodology on a comprehensive 10-task benchmark and demonstrate its power through novel scientific inquiries. Critically, we establish the external validity of our approach by modeling a real-world U.S. tariff shock, showing that agent behaviors align with observed market reactions only when their cognitive architecture is appropriately configured with memory and tools. Our work provides a rigorous, open-source foundation for building and evaluating LLM agents, aimed at fostering more cumulative and scientifically grounded research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21862 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reimagining Agent-based Modeling with Large Language Model Agents via Shachi Kuroki, So Tian, Yingtao Misaki, Kou Ikegami, Takashi Akiba, Takuya Tang, Yujin Artificial Intelligence Multiagent Systems Social and Information Networks General Economics Economics The study of emergent behaviors in large language model (LLM)-driven multi-agent systems is a critical research challenge, yet progress is limited by a lack of principled methodologies for controlled experimentation. To address this, we introduce Shachi, a formal methodology and modular framework that decomposes an agent's policy into core cognitive components: Configuration for intrinsic traits, Memory for contextual persistence, and Tools for expanded capabilities, all orchestrated by an LLM reasoning engine. This principled architecture moves beyond brittle, ad-hoc agent designs and enables the systematic analysis of how specific architectural choices influence collective behavior. We validate our methodology on a comprehensive 10-task benchmark and demonstrate its power through novel scientific inquiries. Critically, we establish the external validity of our approach by modeling a real-world U.S. tariff shock, showing that agent behaviors align with observed market reactions only when their cognitive architecture is appropriately configured with memory and tools. Our work provides a rigorous, open-source foundation for building and evaluating LLM agents, aimed at fostering more cumulative and scientifically grounded research. |
| title | Reimagining Agent-based Modeling with Large Language Model Agents via Shachi |
| topic | Artificial Intelligence Multiagent Systems Social and Information Networks General Economics Economics |
| url | https://arxiv.org/abs/2509.21862 |