# FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering

arXiv: https://arxiv.org/abs/2607.18102 · HTML: https://mlsanity.com/paper/2607.18102/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 25 of 25)

- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters](https://mlsanity.com/paper/2305.12002/) (2023)
- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization](https://mlsanity.com/paper/2411.06018/) (2024)
- [FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis](https://mlsanity.com/paper/2308.01430/) (2023)
- [Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking](https://mlsanity.com/paper/2505.11065/) (2025)
- [FinSage: A Multi-aspect RAG System for Financial Filings Question Answering](https://mlsanity.com/paper/2504.14493/) (2025)
- [FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.15800/) (2025)
- [FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain](https://mlsanity.com/paper/2505.17471/) (2025)
- [FinSight: Towards Real-World Financial Deep Research](https://mlsanity.com/paper/2510.16844/) (2025)
- [Systematic Evaluation of Long-Context LLMs on Financial Concepts](https://mlsanity.com/paper/2412.15386/) (2024)
- [FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios](https://mlsanity.com/paper/2507.10448/) (2025)
- [Query Decomposition for RAG: Balancing Exploration-Exploitation](https://mlsanity.com/paper/2510.18633/) (2025)
- [GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction](https://mlsanity.com/paper/2503.15564/) (2025)
- [Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning](https://mlsanity.com/paper/2505.17086/) (2025)
- [TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding](https://mlsanity.com/paper/2509.14671/) (2025)
- [VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering](https://mlsanity.com/paper/2510.10828/) (2025)
- [FinS-Pilot: A Benchmark for Online Financial RAG System](https://mlsanity.com/paper/2506.02037/) (2025)

## Abstract (arXiv)

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.