ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.08726
22
0

Improved LLM Agents for Financial Document Question Answering

10 June 2025
Nelvin Tan
Zian Seng
Liang Zhang
Yu-Ching Shih
Dong Yang
Amol Salunkhe
ArXiv (abs)PDFHTML
Abstract

Large language models (LLMs) have shown impressive capabilities on numerous natural language processing tasks. However, LLMs still struggle with numerical question answering for financial documents that include tabular and textual data. Recent works have showed the effectiveness of critic agents (i.e., self-correction) for this task given oracle labels. Building upon this framework, this paper examines the effectiveness of the traditional critic agent when oracle labels are not available, and show, through experiments, that this critic agent's performance deteriorates in this scenario. With this in mind, we present an improved critic agent, along with the calculator agent which outperforms the previous state-of-the-art approach (program-of-thought) and is safer. Furthermore, we investigate how our agents interact with each other, and how this interaction affects their performance.

View on arXiv
@article{tan2025_2506.08726,
  title={ Improved LLM Agents for Financial Document Question Answering },
  author={ Nelvin Tan and Zian Seng and Liang Zhang and Yu-Ching Shih and Dong Yang and Amol Salunkhe },
  journal={arXiv preprint arXiv:2506.08726},
  year={ 2025 }
}
Main:6 Pages
5 Figures
Bibliography:2 Pages
6 Tables
Appendix:4 Pages
Comments on this paper