mlsanityData to 14 Oct 2026

MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration

arXiv 2605.25030 ↗First posted 24 May 2026cs.LGcited by 0

On the map: Retrieval-augmented generation → Legal and financial RAG

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (LLMs), a requirement for reliable, financial analysis where answers must be grounded in verifiable evidence from filings rather than generated from model priors. However, designing RAG systems that extract meaningful insights from mixed financial documents and integrate into analyst workflows remains challenging. This paper introduces MimirRAG (Metadata-Integrated Multi-Agent Information Retrieval), a multi-agent RAG system developed iteratively to address these challenges. MimirRAG features a modular pipeline encompassing structure-preserving parsing of PDF filings, table-aware chunking, metadata extraction, agent-based retrieval with query planning and hybrid search, validation, and context-aware generation with numerical reasoning support. Our ablation study identifies three key technical enablers for effective financial RAG: metadata integration, table-aware chunking, and an agentic workflow. MimirRAG was evaluated quantitatively using FinanceBench and qualitatively through expert validation with four financial analysts. The system achieved 89.3% accuracy on FinanceBench, outperforming the original benchmark baselines. Expert feedback highlighted that successful deployment also requires calibrated trust, comprehensive data integration, and user personalization. We conclude that combining multi-agent RAG architecture with human-centric design principles can improve the extraction of meaningful insights in financial analysis.

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 37 of its 54 references that are in the map. First posted on arXiv 24 May 2026.

Builds on

37 of 54 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation22 Apr
  2. 2025Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems19 Mar
  3. 2024Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge23 Nov
  4. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction9 Aug
  5. 2024AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework19 Mar

Other references · 32

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2024A Survey on LLM-as-a-Judgecited by 1,423
  6. 2023BloombergGPT: A Large Language Model for Financecited by 939
  7. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  8. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  9. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
  10. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
  11. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  12. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 195
20 more
  1. 2020Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthycited by 183
  2. 2025MMTEB: Massive Multilingual Text Embedding Benchmarkcited by 125
  3. 2024Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinementcited by 114
  4. 2024A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengescited by 90
  5. 2023FinGPT: Democratizing Internet-scale Data for Financial Large Language Modelscited by 67
  6. 2024Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Modelscited by 61
  7. 2024Arctic-Embed 2.0: Multilingual Retrieval Without Compromisecited by 58
  8. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documentscited by 49
  9. 2024Financial Report Chunking for Effective Retrieval Augmented Generationcited by 46
  10. 2024FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Modelscited by 40
  11. 2024Long Context RAG Performance of Large Language Modelscited by 23
  12. 2025FinMTEB: Finance Massive Text Embedding Benchmarkcited by 18
  13. 2024SEC-QA: A Systematic Evaluation Corpus for Financial QAcited by 17
  14. 2024Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadatacited by 16
  15. 2023Towards reducing hallucination in extracting information from financial reports using Large Language Modelscited by 11
  16. 2024Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Studycited by 11
  17. 2024Struct-X: Enhancing Large Language Models Reasoning with Structured Datacited by 11
  18. 2024FinRobot: AI Agent for Equity Research and Valuation with Large Language Modelscited by 10
  19. 2024Combining Financial Data and News Articles for Stock Price Movement Prediction Using Large Language Modelscited by 6
  20. 2024Multi-Document Financial Question Answering using LLMscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
  2. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
  3. 2026Agentic Retrieval-Augmented Generation for Financial Document Question Answering
  4. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
  5. 2026Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
  6. 2025Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation
  7. 2026Hierarchical Reranking for Scalable Financial RAG System
  8. 2025VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering