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

arXiv: https://arxiv.org/abs/2512.22608 · HTML: https://mlsanity.com/paper/2512.22608/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 99 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist](https://mlsanity.com/paper/2402.18485/) (2024)
- [GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning](https://mlsanity.com/paper/2405.20139/) (2024)
- [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024)
- [Scientific Large Language Models: A Survey on Biological & Chemical Domains](https://mlsanity.com/paper/2401.14656/) (2024)
- [USimAgent: Large Language Models for Simulating Search Users](https://mlsanity.com/paper/2403.09142/) (2024)
- [A Fused Large Language Model for Predicting Startup Success](https://mlsanity.com/paper/2409.03668/) (2024)
- [Finding the unicorn: Predicting early stage startup success through a hybrid intelligence method](https://mlsanity.com/paper/2105.03360/) (2021)
- [SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performance](https://mlsanity.com/paper/2405.19456/) (2024)
- [Graph Neural Network Based VC Investment Success Prediction](https://mlsanity.com/paper/2105.11537/) (2021)
- [Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models](https://mlsanity.com/paper/2412.07144/) (2024)
- [Automating Venture Capital: Founder assessment using LLM-powered segmentation, feature engineering and automated labeling techniques](https://mlsanity.com/paper/2407.04885/) (2024)
- [Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems](https://mlsanity.com/paper/2505.12467/) (2025)
- [Supervised learning for the prediction of firm dynamics](https://mlsanity.com/paper/2009.06413/) (2020)
- [Enhancing Startup Success Predictions in Venture Capital: A GraphRAG Augmented Multivariate Time Series Method](https://mlsanity.com/paper/2408.09420/) (2024)

## Built on by (most cited first, 1 of 1)

- [FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering](https://mlsanity.com/paper/2601.06992/) (2026)

## Abstract (arXiv)

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.