DIALECTIC: A Multi-Agent System for Startup Evaluation

TL;DR

DIALECTIC is an LLM-based multi-agent system designed to evaluate startup investment opportunities by organizing facts, generating arguments, and providing decision scores, thereby aiding venture capitalists in efficient screening.

Contribution

The paper introduces DIALECTIC, a novel multi-agent system that automates startup evaluation using hierarchical fact organization and simulated debate, improving screening efficiency.

Findings

DIALECTIC matches human VC precision in predicting startup success.

The system effectively organizes facts into hierarchical structures.

It provides reliable numeric scores for investment prioritization.

Abstract

Venture capital (VC) investors face a large number of investment opportunities but only invest in few of these, with even fewer ending up successful. Early-stage screening of opportunities is often limited by investor bandwidth, demanding tradeoffs between evaluation diligence and number of opportunities assessed. To ease this tradeoff, we introduce DIALECTIC, an LLM-based multi-agent system for startup evaluation. DIALECTIC first gathers factual knowledge about a startup and organizes these facts into a hierarchical question tree. It then synthesizes the facts into natural-language arguments for and against an investment and iteratively critiques and refines these arguments through a simulated debate, which surfaces only the most convincing arguments. Our system also produces numeric decision scores that allow investors to rank and thus efficiently prioritize opportunities. We evaluate DIALECTIC through backtesting on real investment opportunities aggregated from five VC funds, showing that DIALECTIC matches the precision of human VCs in predicting startup success.