Saved in:
Bibliographic Details
Main Authors: Yoshizato, Konosuke, Shimizu, Kazuma, Higa, Ryota, Otsuka, Takanobu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.05524
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914307786145792
author Yoshizato, Konosuke
Shimizu, Kazuma
Higa, Ryota
Otsuka, Takanobu
author_facet Yoshizato, Konosuke
Shimizu, Kazuma
Higa, Ryota
Otsuka, Takanobu
contents This study investigates large language model (LLM) -based multi-agent systems (MASs) as a promising approach to inventory management, which is a key component of supply chain management. Although these systems have gained considerable attention for their potential to address the challenges associated with typical inventory management methods, key uncertainties regarding their effectiveness persist. Specifically, it is unclear whether LLM-based MASs can consistently derive optimal ordering policies and adapt to diverse supply chain scenarios. To address these questions, we examine an LLM-based MAS with a fixed-ordering strategy prompt that encodes the stepwise processes of the problem setting and a safe-stock strategy commonly used in inventory management. Our empirical results demonstrate that, even without detailed prompt adjustments, an LLM-based MAS can determine optimal ordering decisions in a restricted scenario. To enhance adaptability, we propose a novel agent called AIM-RM, which leverages similar historical experiences through similarity matching. Our results show that AIM-RM outperforms benchmark methods across various supply chain scenarios, highlighting its robustness and adaptability.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05524
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory Retrieval
Yoshizato, Konosuke
Shimizu, Kazuma
Higa, Ryota
Otsuka, Takanobu
Multiagent Systems
Artificial Intelligence
This study investigates large language model (LLM) -based multi-agent systems (MASs) as a promising approach to inventory management, which is a key component of supply chain management. Although these systems have gained considerable attention for their potential to address the challenges associated with typical inventory management methods, key uncertainties regarding their effectiveness persist. Specifically, it is unclear whether LLM-based MASs can consistently derive optimal ordering policies and adapt to diverse supply chain scenarios. To address these questions, we examine an LLM-based MAS with a fixed-ordering strategy prompt that encodes the stepwise processes of the problem setting and a safe-stock strategy commonly used in inventory management. Our empirical results demonstrate that, even without detailed prompt adjustments, an LLM-based MAS can determine optimal ordering decisions in a restricted scenario. To enhance adaptability, we propose a novel agent called AIM-RM, which leverages similar historical experiences through similarity matching. Our results show that AIM-RM outperforms benchmark methods across various supply chain scenarios, highlighting its robustness and adaptability.
title AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory Retrieval
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2602.05524