FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios
This addresses the need for more accurate and comprehensive financial analysis tools for financial companies, though it is incremental as it builds on existing multi-agent and LLM approaches.
The paper tackles the problem of generating comprehensive financial reports by proposing FinTeam, a multi-agent collaborative system with four specialized LLM agents, which achieved a 62.00% acceptance rate in human evaluations, outperforming baseline models like GPT-4o and Xuanyuan.
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/.