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

2025-07-05

AI Summary

Current large language models (LLMs), fine-tuned on simple question-answering tasks, lack the capability to address the complexity of real-world financial scenarios—specifically, macro-micro interdependencies, multi-source data integration, and cross-functional collaboration. To bridge this gap, we propose a multi-agent collaborative framework for financial report generation, inspired by institutional departmental roles. The framework comprises four specialized agents: Document Analyst, Economic Analyst, Accounting Auditor, and Investment Advisor, jointly trained on a domain-adapted dataset. It supports hierarchical task decomposition, multi-stage inter-agent coordination, and end-to-end report synthesis. Evaluated on real investment forum data, the system achieves a human acceptance rate of 62.00%. On the FinCUGE and FinEval benchmarks, it improves average accuracy by 7.43% and 2.06%, respectively. Our approach significantly enhances the systematicity, domain expertise, and interpretability of automated financial analysis.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Multiagent Systems: Coordination and Collaboration
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

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/.

Problem

• Existing LLMs fail to analyze complex financial scenarios comprehensively
• Financial tasks require multi-department expertise but lack integrated solutions
• Current models underperform in generating accurate financial reports

Innovation

• Multi-agent system with four specialized LLM agents
• Agents trained with specific financial expertise datasets
• Outperforms GPT-4o and Xuanyuan in financial tasks