FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios

TL;DR

FinTeam is a multi-agent system that leverages specialized LLM agents to generate comprehensive financial reports, outperforming baseline models in accuracy and acceptance rate on real-world financial analysis tasks.

Contribution

Introduces FinTeam, a collaborative multi-agent framework with specialized financial agents trained on domain-specific datasets for improved financial analysis and report generation.

Findings

Achieved 62% acceptance rate in human evaluations, surpassing GPT-4o and Xuanyuan.

Demonstrated 7.43% average improvement on FinCUGE.

Achieved 2.06% higher accuracy on FinEval.

Abstract

Financial report generation tasks range from macro- to micro-economics analysis, also requiring extensive data analysis. Existing LLM models are usually fine-tuned on simple QA tasks and cannot comprehensively analyze real financial scenarios. Given the complexity, financial companies often distribute tasks among departments. Inspired by this, we propose FinTeam, a financial multi-agent collaborative system, with a workflow with four LLM agents: document analyzer, analyst, accountant, and consultant. We train these agents with specific financial expertise using constructed datasets. We evaluate FinTeam on comprehensive financial tasks constructed from real online investment forums, including macroeconomic, industry, and company analysis. The human evaluation shows that by combining agents, the financial reports generate from FinTeam achieved a 62.00% acceptance rate, outperforming baseline models like GPT-4o and Xuanyuan. Additionally, FinTeam's agents demonstrate a 7.43% average improvement on FinCUGE and a 2.06% accuracy boost on FinEval. Project is available at https://github.com/FudanDISC/DISC-FinLLM/.