AgentFinVQA：一种可部署的多智能体管道用于可审计的金融图表问答
AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA
AI总结：
提出多智能体管道AgentFinVQA，通过分解查询步骤并记录可追溯的模型评估包，在金融图表问答中实现可审计性与本地部署，在FinMME上提升准确率7.68个百分点。
摘要：
在受监管环境中的金融图表问答不仅要求准确性：从业者必须在采取行动之前知道哪些答案值得信任，而且许多机构无法将客户数据发送给外部模型提供商。然而，现有的图表问答智能体注重准确性且不透明，并且大多数假设专有API访问；据我们所知，没有一种方法能在不显著牺牲准确性的情况下同时实现可审计性和本地部署。我们提出AgentFinVQA，一个多智能体管道，将每个查询分解为规划、OCR、图例定位、视觉检查和验证，每个样本记录在可追溯的模型评估包（MEP）中。在FinMME上，AgentFinVQA在使用专有主干（Gemini-3 Flash；71.24% vs. 63.56%，McNemar p ≈ 1.1×10^{-16}）时比主骨干匹配的零样本基线提高+7.68个百分点，在使用本地服务的开放权重Qwen3.6-27B-FP8时提高+4.84个百分点。验证器的判断也作为有用的置信度信号（确认答案与修正答案的精确准确率分别为68.2%和55.6%），支持人在回路审查路由。错误分析表明，问题误解、图例混淆和提取错误占失败原因的近三分之二，并且是验证器检测最少的类别，为未来工作指明了明确方向。这些结果共同表明，可审计、本地部署的金融图表问答是可行的，并且开放权重系统保留了大部分准确率提升，同时实现了完全的数据驻留。我们发布代码以支持可重复评估。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
