---
title: "Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agents"
authors:
  - "Zhongyang Liu"
  - "Haoyu Pei"
  - "Xiangyi Xiao"
  - "Xiaocong Du"
  - "Yihui Li"
  - "Suting Hong"
  - "Kunpeng Zhang"
  - "Haipeng Zhang"
doi: "10.24963/ijcai.2026/721"
url: "https://ijcai.org/proceedings/2026/721"
pdf: "https://ijcai.org/proceedings/2026/0721.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6480-6490"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Domain-specific AI4Tech: AI4Finance"
---

# Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agents

Zhongyang Liu, Haoyu Pei, Xiangyi Xiao, Xiaocong Du, Yihui Li, Suting Hong, Kunpeng Zhang, Haipeng Zhang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6480-6490. DOI: [10.24963/ijcai.2026/721](https://doi.org/10.24963/ijcai.2026/721)

## Abstract

Due to the high value and high failure rates of startups, predicting their success is a critical challenge. Existing approaches typically model startup success from a single decision-maker's perspective, overlooking the collective dynamics that dominate real-world venture capital (VC) decision-making. We propose SimVC-CAS, a collective agent system that simulates VC decisions 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 investor network dynamics. Each agent represents an investor with distinct traits and preferences, enabling heterogeneous evaluations and realistic information exchange over a graph-structured co-investment network.
Using both proprietary and public VC data with strict anti-leakage controls, we show that SimVC-CAS significantly improves predictive performance, achieving approximately 25% relative improvement in average precision@10, while exhibiting consistency with real investor decisions. The interaction mechanism is particularly effective for network-central startups, confirming the importance of network in VC decision-making. Analysis of agents' reasoning for decision changes further reveals how network environment influence decision quality, demonstrating the system's interpretability. Our approach may generalize to broader group decision-making scenarios. Our code is available at https://github.com/ZhangDataLab/SimVC-CAS.