A Multi-Agent Orchestration Framework for Venture Capital Due Diligence

TL;DR

This paper introduces an automated multi-agent system combining LLMs and web retrieval for venture capital due diligence, emphasizing data accuracy and transparency.

Contribution

It presents a novel orchestration framework with a programmatic extraction pipeline and fallback mechanisms to improve financial data reliability.

Findings

Successfully retrieves and parses official financial filings.

Explicitly flags missing data to prevent hallucinations.

Workflow artifacts are publicly available for replication.

Abstract

We present a fully automated multi-agent framework for corporate due diligence and market analysis in venture capital. The system runs on an event-driven orchestration architecture, combining Large Language Models (LLMs) with real-time web retrieval to synthesize unstructured data into structured investment intelligence. A central technical contribution is a programmatic extraction pipeline that reverse-engineers the frontend-to-backend communication of the Greek Business Registry ($\Gamma$.E.MH.), querying dynamic endpoints to retrieve official financial filings that are then parsed using a layout-aware OCR extractor. A structural fallback mechanism explicitly flags data absence rather than generating unverified figures, directly targeting hallucination in financial contexts. All workflow artifacts are publicly available to support replication.