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.
@article{arxiv.2509.17395,
title = {FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis},
author = {Tianshi Cai and Guanxu Li and Nijia Han and Ce Huang and Zimu Wang and Changyu Zeng and Yuqi Wang and Jingshi Zhou and Haiyang Zhang and Qi Chen and Yushan Pan and Shuihua Wang and Wei Wang},
journal= {arXiv preprint arXiv:2509.17395},
year = {2025}
}
Comments
Accepted at FinNLP@EMNLP 2025. Camera-ready version