FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914050493906944 |
|---|---|
| author | Cai, Tianshi Li, Guanxu Han, Nijia Huang, Ce Wang, Zimu Zeng, Changyu Wang, Yuqi Zhou, Jingshi Zhang, Haiyang Chen, Qi Pan, Yushan Wang, Shuihua Wang, Wei |
| author_facet | Cai, Tianshi Li, Guanxu Han, Nijia Huang, Ce Wang, Zimu Zeng, Changyu Wang, Yuqi Zhou, Jingshi Zhang, Haiyang Chen, Qi Pan, Yushan Wang, Shuihua Wang, Wei |
| contents | We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized agents, covering earnings, market, sentiment, valuation, and risk, run in parallel to synthesize evidence into multi-dimensional insights. To mitigate overconfidence and improve reliability, we introduce a safe debate protocol that enables agents to challenge and refine initial conclusions while preserving coherent recommendations. Experimental results, based on both LLM-based and human evaluations, demonstrate the framework's efficacy in producing high-quality analysis with calibrated confidence levels and actionable investment strategies across multiple time horizons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17395 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis Cai, Tianshi Li, Guanxu Han, Nijia Huang, Ce Wang, Zimu Zeng, Changyu Wang, Yuqi Zhou, Jingshi Zhang, Haiyang Chen, Qi Pan, Yushan Wang, Shuihua Wang, Wei Computation and Language We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized agents, covering earnings, market, sentiment, valuation, and risk, run in parallel to synthesize evidence into multi-dimensional insights. To mitigate overconfidence and improve reliability, we introduce a safe debate protocol that enables agents to challenge and refine initial conclusions while preserving coherent recommendations. Experimental results, based on both LLM-based and human evaluations, demonstrate the framework's efficacy in producing high-quality analysis with calibrated confidence levels and actionable investment strategies across multiple time horizons. |
| title | FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.17395 |