{"ID":2865019,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21862","arxiv_id":"2509.21862","title":"Reimagining Agent-based Modeling with Large Language Model Agents via Shachi","abstract":"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.","short_abstract":"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 age...","url_abs":"https://arxiv.org/abs/2509.21862","url_pdf":"https://arxiv.org/pdf/2509.21862v2","authors":"[\"So Kuroki\",\"Yingtao Tian\",\"Kou Misaki\",\"Takashi Ikegami\",\"Takuya Akiba\",\"Yujin Tang\"]","published":"2025-09-26T04:38:59Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.MA\",\"cs.SI\",\"econ.GN\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}