Saved in:
Bibliographic Details
Main Authors: Koshkin, Roman, Dai, Pengyu, Fujikawa, Nozomi, Togami, Masahito, Visentini-Scarzanella, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912516425121792
author Koshkin, Roman
Dai, Pengyu
Fujikawa, Nozomi
Togami, Masahito
Visentini-Scarzanella, Marco
author_facet Koshkin, Roman
Dai, Pengyu
Fujikawa, Nozomi
Togami, Masahito
Visentini-Scarzanella, Marco
contents We present an autonomous framework that leverages Large Language Models (LLMs) to automate end-to-end business analysis and market report generation. At its core, the system employs specialized agents - Researcher, Reviewer, Writer, and Retriever - that collaborate to analyze data and produce comprehensive reports. These agents learn from real professional consultants' presentation materials at Amazon through in-context learning to replicate professional analytical methodologies. The framework executes a multi-step process: querying databases, analyzing data, generating insights, creating visualizations, and composing market reports. We also introduce a novel LLM-based evaluation system for assessing report quality, which shows alignment with expert human evaluations. Building on these evaluations, we implement an iterative improvement mechanism that optimizes report quality through automated review cycles. Experimental results show that report quality can be improved by both automated review cycles and consultants' unstructured knowledge. In experimental validation, our framework generates detailed 6-page reports in 7 minutes at a cost of approximately \$1. Our work could be an important step to automatically create affordable market insights.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01370
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MaRGen: Multi-Agent LLM Approach for Self-Directed Market Research and Analysis
Koshkin, Roman
Dai, Pengyu
Fujikawa, Nozomi
Togami, Masahito
Visentini-Scarzanella, Marco
Computation and Language
Information Retrieval
We present an autonomous framework that leverages Large Language Models (LLMs) to automate end-to-end business analysis and market report generation. At its core, the system employs specialized agents - Researcher, Reviewer, Writer, and Retriever - that collaborate to analyze data and produce comprehensive reports. These agents learn from real professional consultants' presentation materials at Amazon through in-context learning to replicate professional analytical methodologies. The framework executes a multi-step process: querying databases, analyzing data, generating insights, creating visualizations, and composing market reports. We also introduce a novel LLM-based evaluation system for assessing report quality, which shows alignment with expert human evaluations. Building on these evaluations, we implement an iterative improvement mechanism that optimizes report quality through automated review cycles. Experimental results show that report quality can be improved by both automated review cycles and consultants' unstructured knowledge. In experimental validation, our framework generates detailed 6-page reports in 7 minutes at a cost of approximately \$1. Our work could be an important step to automatically create affordable market insights.
title MaRGen: Multi-Agent LLM Approach for Self-Directed Market Research and Analysis
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2508.01370