FIN-SIGHT AI: A Hybrid Multi-Agent Generative AI Framework for Automated Financial Report Analysis
FIN-SIGHT AI presents a hybrid multi-agent Generative AI framework for financial report analysis. The framework combines Retrieval-Augmented Generation (RAG), hybrid retrieval, and LangGraph-based agent orchestration to support financial document understanding and analytical workflows. The proposed architecture integrates FAISS-based vector retrieval and BM25-based keyword retrieval with specialized agents for financial research, analysis, ratio evaluation, risk assessment, validation, and report generation. This work explores the application of Generative AI and multi-agent systems to financial document analysis and structured financial insights.
Authors
- PRIYADHARSHINI S
- Sridevi S
- Swathi G
- Shree Abiraami M
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-07
- DOI
- https://doi.org/10.5281/zenodo.24031954
- Primary Topic
- Topic Modeling
- Type
- preprint