FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913940170080256 |
|---|---|
| author | Wu, Yingqian Wang, Qiushi Long, Zefei Ye, Rong Lu, Zhongtian Zhang, Xianyin Li, Bingxuan Chen, Wei Zhang, Liwen Wei, Zhongyu |
| author_facet | Wu, Yingqian Wang, Qiushi Long, Zefei Ye, Rong Lu, Zhongtian Zhang, Xianyin Li, Bingxuan Chen, Wei Zhang, Liwen Wei, Zhongyu |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10448 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios Wu, Yingqian Wang, Qiushi Long, Zefei Ye, Rong Lu, Zhongtian Zhang, Xianyin Li, Bingxuan Chen, Wei Zhang, Liwen Wei, Zhongyu Computational Engineering, Finance, and Science Machine Learning 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/. |
| title | FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios |
| topic | Computational Engineering, Finance, and Science Machine Learning |
| url | https://arxiv.org/abs/2507.10448 |