P1GPT: a multi-agent LLM workflow module for multi-modal financial information analysis

TL;DR

P1GPT is a layered multi-agent LLM framework that unifies multi-modal financial data analysis and decision-making, demonstrating improved trading performance and interpretability in backtests.

Contribution

It introduces a structured reasoning pipeline for multi-modal financial analysis, moving beyond role simulation to systematic data fusion and explanation.

Findings

Achieves superior returns and risk-adjusted performance in backtests

Maintains low drawdowns during trading periods

Provides transparent causal rationales for decisions

Abstract

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.