mlsanityData to 14 Oct 2026

Towards Expert Financial QA via Self-Improving RAG

arXiv 2608.26706 ↗First posted 27 Aug 2026cs.CLcited by 0

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

Abstract (arXiv)

Expert-level financial question answering requires both grounded verification to catch numeric hallucinations and audit trails for regulatory compliance, attributes that standard single-pass RAG systems lack. We take a step toward this goal with Self-Improving RAG, a framework that decomposes document QA into three specialized agents (Retrieval, Reasoning, and Judge) coordinated by an orchestrator with feedback-driven self-correction. When the Judge Agent scores an answer below a dynamic threshold, the system triggers retry with escalated strategies: broader retrieval, more careful prompting, and relaxed acceptance criteria. We evaluate on FinanceBench (SEC filing QA), where Self-Improving RAG achieves 86% oracle-guided accuracy (measuring agreement with gold answers) with a 36.4% Lazarus Rate, recovering nearly 4 in 10 initially incorrect answers through targeted retry. A key finding is that a fixed retrieval pipeline with judge-driven retry achieves strong results without dynamic routing, providing full interpretability. Every decision is logged with confidence scores, enabling the audit trails required for regulated financial applications.

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 11 of its 16 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

11 of 16 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering12 Oct

Other references · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  6. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  7. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  8. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  9. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  10. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic Retrieval-Augmented Generation for Financial Document Question Answering
  2. 2025SMARTFinRAG: Interactive Modularized Financial RAG Benchmark
  3. 2025Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
  4. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
  5. 2026Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering
  6. 2026BudgetVerify: Budget-Tiered Verification for Financial QA
  7. 2026MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
  8. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation