发表机构
1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles 5The Chinese University of Hong Kong 6University of Manitoba 7Universit\'e de Montr\'eal 8Boston University 9Mila - Quebec AI Institute 10CG Matrix Technology Limited 11Lakehead University 12McMaster University
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对美国证券交易委员会文件问答中模型与文件不匹配问题，提出FinSAgent框架，通过角色专用智能体、数据库感知查询分解及多路径检索等方法，提升检索覆盖和答案正确性，在离线和在线实验中均优于基线。
AI 中文摘要
关于美国证券交易委员会（SEC）文件的金融问答需要检索和综合分散在冗长、标准化且高度冗余披露中的异构证据。现有检索增强和多智能体系统通常直接从用户问题派生检索查询并按语义相似性对候选进行排名，这导致模型先验与目标文件的结构、术语和证据标准不匹配。我们提出了FinSAgent，一个基于证据的多智能体框架，它将SEC文件问答重新构建为语料库对齐的检索规划，并以单一原则纠正两端：在模型先验可能占主导的任何地方注入语料库侧条件。FinSAgent结合了（1）锚定在规定的10-K项目结构上的角色专用智能体，（2）数据库感知查询分解，根据本地语料库的轻量级摘要级视图对每个智能体的子查询进行条件设定，以及（3）多路径检索和学习到的特征门控重排器，将证据有效性与语义相似性分开。在五个离线金融问答基准测试中，FinSAgent在检索覆盖范围和答案正确性方面优于强大的单智能体和多智能体基线；在一项有1000个匿名用户评分的三臂随机在线实验中，它也比基线获得更高的分数。
英文摘要
Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardized, and highly redundant disclosures. Existing retrieval-augmented and multi-agent systems typically derive retrieval queries directly from the user's question and rank candidates by semantic similarity. Together, these choices create prior-corpus misalignment: a mismatch between model priors and the target filings' structure, terminology, and evidence standards. As a result, query generation misses corpus-specific evidence, while semantic reranking favors topically similar but evidentially invalid false-positive chunks. We propose FinSAgent, an evidence-grounded multi-agent framework that reframes SEC filing QA as corpus-aligned retrieval planning and corrects both ends with a single principle: inject corpus-side conditioning wherever model priors would otherwise dominate. FinSAgent combines (1) role-specialized agents anchored to the mandated 10-K item structure, (2) database-aware query decomposition that conditions each agent's sub-queries on a lightweight, summary-level view of the local corpus, and (3) multi-path retrieval with a learned feature-gated reranker that separates evidential validity from semantic similarity. Across five offline financial QA benchmarks, FinSAgent improves retrieval coverage and answer correctness over strong single-agent and multi-agent baselines; in a three-arm randomized online experiment with 1,000 anonymous user ratings, it also receives higher scores than baselines.
Comments20 pages, 14 figures, 9 tables
