Saved in:
Bibliographic Details
Main Authors: Lu, Chen-Che, Chou, Yun-Cheng, Chen, Teng-Ruei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.23032
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914116283662336
author Lu, Chen-Che
Chou, Yun-Cheng
Chen, Teng-Ruei
author_facet Lu, Chen-Che
Chou, Yun-Cheng
Chen, Teng-Ruei
contents Recent advances in large language models (LLMs) have enabled multi-agent reasoning systems capable of collaborative decision-making. However, in financial analysis, most frameworks remain narrowly focused on either isolated single-agent predictors or loosely connected analyst ensembles, and they lack a coherent reasoning workflow that unifies diverse data modalities. We introduce P1GPT, a layered multi-agent LLM framework for multi-modal financial information analysis and interpretable trading decision support. Unlike prior systems that emulate trading teams through role simulation, P1GPT implements a structured reasoning pipeline that systematically fuses technical, fundamental, and news-based insights through coordinated agent communication and integration-time synthesis. Backtesting on multi-modal datasets across major U.S. equities demonstrates that P1GPT achieves superior cumulative and risk-adjusted returns, maintains low drawdowns, and provides transparent causal rationales. These findings suggest that structured reasoning workflows, rather than agent role imitation, offer a scalable path toward explainable and trustworthy financial AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle P1GPT: a multi-agent LLM workflow module for multi-modal financial information analysis
Lu, Chen-Che
Chou, Yun-Cheng
Chen, Teng-Ruei
Computational Engineering, Finance, and Science
Recent advances in large language models (LLMs) have enabled multi-agent reasoning systems capable of collaborative decision-making. However, in financial analysis, most frameworks remain narrowly focused on either isolated single-agent predictors or loosely connected analyst ensembles, and they lack a coherent reasoning workflow that unifies diverse data modalities. We introduce P1GPT, a layered multi-agent LLM framework for multi-modal financial information analysis and interpretable trading decision support. Unlike prior systems that emulate trading teams through role simulation, P1GPT implements a structured reasoning pipeline that systematically fuses technical, fundamental, and news-based insights through coordinated agent communication and integration-time synthesis. Backtesting on multi-modal datasets across major U.S. equities demonstrates that P1GPT achieves superior cumulative and risk-adjusted returns, maintains low drawdowns, and provides transparent causal rationales. These findings suggest that structured reasoning workflows, rather than agent role imitation, offer a scalable path toward explainable and trustworthy financial AI systems.
title P1GPT: a multi-agent LLM workflow module for multi-modal financial information analysis
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2510.23032