# DIALECTIC: A Multi-Agent System for Startup Evaluation

arXiv: https://arxiv.org/abs/2603.12274 · HTML: https://mlsanity.com/paper/2603.12274/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 60 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 13 of 13)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions](https://mlsanity.com/paper/2311.13982/) (2023)
- [DEBATE: Devil's Advocate-Based Assessment and Text Evaluation](https://mlsanity.com/paper/2405.09935/) (2024)
- [A Fused Large Language Model for Predicting Startup Success](https://mlsanity.com/paper/2409.03668/) (2024)
- [GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees](https://mlsanity.com/paper/2411.08257/) (2024)
- [Finding the unicorn: Predicting early stage startup success through a hybrid intelligence method](https://mlsanity.com/paper/2105.03360/) (2021)
- [STRUX: An LLM for Decision-Making with Structured Explanations](https://mlsanity.com/paper/2410.12583/) (2024)
- [Founder-GPT: Self-play to evaluate the Founder-Idea fit](https://mlsanity.com/paper/2312.12037/) (2023)
- [Improving Startup Success with Text Analysis](https://mlsanity.com/paper/2312.06236/) (2023)
- [Automating Venture Capital: Founder assessment using LLM-powered segmentation, feature engineering and automated labeling techniques](https://mlsanity.com/paper/2407.04885/) (2024)

## Built on by (most cited first, 2 of 2)

- [From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Under Delayed Ground Truth](https://mlsanity.com/paper/2607.10972/) (2026)
- [Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation](https://mlsanity.com/paper/2607.12986/) (2026)

## Abstract (arXiv)

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.