LLM Agents as VC investors: Predicting Startup Success via RolePlay-Based Collective Simulation

2025-12-27

AI Summary

This paper addresses the limitation of traditional venture capital (VC) decision modeling—its reliance on individual-level perspectives, which fails to capture the dynamic nature of collective judgment. To bridge this gap, we propose SimVC-CAS: the first VC decision modeling framework that formalizes investment decisions as graph-structured, dynamic interactions among heterogeneous agents (general partners, limited partners, and entrepreneurs), jointly incorporating firm fundamentals and investor network behavioral dynamics. Methodologically, SimVC-CAS integrates large language model–driven role-playing agents with personalized behavioral priors, a graph neural network–supervised interaction module, and a rigorously designed, data-leakage–free empirical training framework grounded in PitchBook data. Experiments demonstrate a 25% relative improvement in mean precision@10 over baselines, alongside substantial gains in predictive accuracy, interpretability, and cross-scenario generalizability—establishing a novel paradigm for collective decision modeling in VC.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Adversarial Agents
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Due to the high value and high failure rate of startups, predicting their success has become a critical challenge across interdisciplinary research. Existing approaches typically model success prediction from the perspective of a single decision-maker, overlooking the collective dynamics of investor groups that dominate real-world venture capital (VC) decisions. In this paper, we propose SimVC-CAS, a novel collective agent system that simulates VC decision-making as a multi-agent interaction process. By designing role-playing agents and a GNN-based supervised interaction module, we reformulate startup financing prediction as a group decision-making task, capturing both enterprise fundamentals and the behavioral dynamics of potential investor networks. Each agent embodies an investor with unique traits and preferences, enabling heterogeneous evaluation and realistic information exchange through a graph-structured co-investment network. Using real-world data from PitchBook and under strict data leakage controls, we show that SimVC-CAS significantly improves predictive accuracy while providing interpretable, multiperspective reasoning, for example, approximately 25% relative improvement with respect to average precision@10. SimVC-CAS also sheds light on other complex group decision scenarios.

Problem

• Predict startup success via multi-agent simulation
• Model collective investor dynamics for VC decisions
• Improve predictive accuracy with interpretable group reasoning

Innovation

• Multi-agent simulation for VC decision-making
• Role-playing agents with unique investor traits
• GNN-based supervised interaction module