David vs. Goliath: Cost-Efficient Financial QA via Cascaded Multi-Agent Reasoning

Chenghao Liu, Qian Liu, Ziqin Zhu, Hao Fei, Aniket Mahanti


Abstract
Large language models (LLMs) have demonstrated remarkable reasoning capabilities, including in financial question answering (FQA). However, the performance in FQA remains limited, particularly in questions that require deep financial knowledge and complex numerical reasoning. While supervised fine-tuning and closed-source LLMs have shown promise, they are often constrained by high costs or computational inefficiency. In this paper, we propose a low-cost yet effective framework, named FinMAN (Financial multi-agent framework), that enables small LLMs (e.g., 8B) to perform complex reasoning tasks without relying on expensive models or task-specific fine-tuning. FinMAN improves formula selection, extraction, and calculation to help small-scale models solve FQA tasks more accurately, with a lightweight verification mechanism to correct common errors. Experimental results show that FinMAN outperforms the best open-source model on BizBench by 10.46% and achieves competitive performance to GPT-3.5 using significantly fewer parameters. Our code and data are publicly available at https://github.com/coenliu/MultiAgentFin.
Anthology ID:
2025.findings-emnlp.225
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4212–4229
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.225/
DOI:
Bibkey:
Cite (ACL):
Chenghao Liu, Qian Liu, Ziqin Zhu, Hao Fei, and Aniket Mahanti. 2025. David vs. Goliath: Cost-Efficient Financial QA via Cascaded Multi-Agent Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 4212–4229, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
David vs. Goliath: Cost-Efficient Financial QA via Cascaded Multi-Agent Reasoning (Liu et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.225.pdf
Checklist:
 2025.findings-emnlp.225.checklist.pdf