DIALECTIC: A Multi-Agent System for Startup Evaluation
On the map: LLM agents and tool use → Financial trading and forecasting agents
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.
Key facts. Cited by 2 papers in the map (data through 7 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.
Builds on
13 of 60 references.
References · 13
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
- 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
- 2023Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questionscited by 19
- 2024DEBATE: Devil's Advocate-Based Assessment and Text Evaluationcited by 16
- 2024A Fused Large Language Model for Predicting Startup Successcited by 13
- 2024GPTree: Towards Explainable Decision-Making via LLM-powered Decision Treescited by 13
- 2021Finding the unicorn: Predicting early stage startup success through a hybrid intelligence methodcited by 10
- 2024STRUX: An LLM for Decision-Making with Structured Explanationscited by 7
- 2023Founder-GPT: Self-play to evaluate the Founder-Idea fitcited by 6
- 2023Improving Startup Success with Text Analysiscited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2024SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performance
- 2026A Multi-Agent Orchestration Framework for Venture Capital Due Diligence
- 2025The Gaining Paths to Investment Success: Information-Driven LLM Graph Reasoning for Venture Capital Prediction
- 2025LLM-AR: LLM-powered Automated Reasoning Framework
- 2026Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents
- 2026Multi-Agent Debate for Explainable Trading: Reasoning, Consensus, and Performance in Simulated Markets
- 2025PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional Features
- 2026BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting