用AI模拟多方辩论，自动评估初创公司投资价值。
DIALECTIC: A Multi-Agent System for Startup Evaluation
- 构建多智能体系统，通过问答树提取事实并生成正反论证。
- 模拟辩论迭代优化观点，输出可排序的决策评分。
- 在五家风投真实数据上验证，预测精度媲美人类投资人。
风险投资（VC）面临海量投资机会，但只能筛选少数，且成功者更少。早期筛选常受限于投资人精力，需在评估深度与覆盖数量间权衡。为此，我们提出DIALECTIC——一个基于大模型的多智能体初创企业评估系统。该系统首先通过问答树结构收集并组织企业事实信息，再将事实合成自然语言的正反论证，并通过模拟辩论迭代批判与优化论点，仅保留最具说服力的观点。系统还生成数值决策分数，帮助投资人高效排序和优先处理项目。我们在五个风投基金的真实投资数据上进行回溯测试，结果表明DIALECTIC在预测初创企业成功方面的精度与人类投资人相当。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。