AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA

Computer Science > Artificial Intelligence [Submitted on 18 Jun 2026] AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA Aravind Narayanan, Shaina Raza Financial chart question answering in regulated settings demands more than accuracy: practitioners must know which answers to trust before acting on them, and many institutions cannot send client data to external model providers. Yet existing chart-QA agents are accuracy-focused and opaque, and most assume proprietary API access; to our knowledge, none combines auditability with on-premise deployability without significant accuracy compromise. We present AgentFinVQA, a multi-agent pipeline that decomposes each query into planning, OCR, legend grounding, visual inspection, and verification, recording every step in a traceable Model Evaluation Packet (MEP) per sample. On FinMME, AgentFinVQA improves +7.68 pp over a primary-backbone matched zero-shot baseline with a proprietary backbone (Gemini-3 Flash; 71.24% vs. 63.56%, McNemar p \approx 1.1 \times 10^{-16}), and +4.84 pp with open-weights Qwen3.6-27B-FP8 served locally. The verifier's verdict also serves as a useful confidence signal (68.2% vs. 55.6% exact accuracy on confirmed vs. revised answers), enabling human-in-the-loop review routing. Error analysis shows that question misunderstanding, legend confusion and extraction error account for nearly two-thirds of failures and are the categories least detected by the verifier, identifying clear directions for future work. Together these results show that auditable, on-premise financial chart QA is practical and that the open-weights system keeps most of the accuracy gains while enabling full data residency. We release our code to support reproducible evaluation. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2606.19782 [cs.AI]   (or arXiv:2606.19782v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.19782 Focus to learn more Submission history From: Aravind Narayanan [view email] [v1] Thu, 18 Jun 2026 04:33:07 UTC (490 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)