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

• URL: http://arxiv.org/abs/2512.22608v1
• Date: Sat, 27 Dec 2025 14:34:44 GMT
• Title: LLM Agents as VC investors: Predicting Startup Success via RolePlay-Based Collective Simulation
• Authors: Zhongyang Liu, Haoyu Pei, Xiangyi Xiao, Xiaocong Du, Yihui Li, Suting Hong, Kunpeng Zhang, Haipeng Zhang,
• Abstract summary: SimVC-CAS is a novel collective agent system that simulates venture capital decision-making as a multi-agent interaction process.<n>We show that SimVC-CAS significantly improves predictive accuracy while providing interpretable, multiperspective reasoning.
• Score: 13.180519641845398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• The Gaining Paths to Investment Success: Information-Driven LLM Graph Reasoning for Venture Capital Prediction [11.661060447479086]
  Most venture capital (VC) investments fail, while a few deliver outsized returns.<n>We present MIRAGE-VC, a multi-perspective retrieval-augmented generation framework that addresses two obstacles: path explosion and heterogeneous evidence fusion.<n>Under strict anti-leakage controls, MIRAGE-VC achieves +5.0% F1 and +16.6% PrecisionAt5, and sheds light on other off-graph prediction tasks.
  arXiv  Detail & Related papers  (2025-12-29T14:20:31Z)
• LLM-Based Multi-Agent System for Simulating and Analyzing Marketing and Consumer Behavior [1.6352616029995921]
  We introduce an LLM-powered multi-agent simulation framework that models consumer decisions and social dynamics.<n>In a price-discount marketing scenario, the system delivers actionable strategy-testing outcomes.
  arXiv  Detail & Related papers  (2025-10-20T23:15:44Z)
• Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading [57.28635022507172]
  TiMi is a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment.<n>We propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection.
  arXiv  Detail & Related papers  (2025-10-06T13:08:55Z)
• What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking [50.72154186522052]
  Large language models (LLMs) excel at processing information reactively but lack the ability to systemically explore hypothetical futures.<n>We propose WiA-LLM, a new paradigm that equips LLMs with proactive thinking capabilities.<n>We validate WiA-LLM in Honor of Kings, a complex multiplayer game environment.
  arXiv  Detail & Related papers  (2025-09-05T04:05:27Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism [8.46483000946212]
  Large language model (LLM)-based agents demonstrate significant potential in financial trading.<n>High sensitivity to market noise undermines the performance of LLM-based trading systems.<n>We propose a novel multi-agent system featuring an internal competitive mechanism inspired by modern corporate management structures.
  arXiv  Detail & Related papers  (2025-08-01T11:48:13Z)
• MASS: Muli-agent simulation scaling for portfolio construction [17.363056358369143]
  We introduce the Multi-Agent Scaling Simulation (MASS), a novel framework that leverages multi-agent simulation for direct, end-to-end portfolio construction.<n>At its core, MASS employs a backward optimization process to dynamically learn the optimal distribution of heterogeneous agents.<n>We demonstrate that as the number of agents increases exponentially (up to 512), the aggregated decisions yield progressively higher excess returns.
  arXiv  Detail & Related papers  (2025-05-15T13:27:18Z)
• EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt Recovery [65.30120701878582]
  Large Language Model (LLM) agents are vulnerable to exploitation in emotion-sensitive domains like debt collection.<n>EmoDebt is an emotional intelligence engine that reframes a model's ability to express emotion in negotiation as a sequential decision-making problem.<n>EmoDebt achieves significant strategic robustness, substantially outperforming non-adaptive and emotion-agnostic baselines.
  arXiv  Detail & Related papers  (2025-03-27T01:41:34Z)
• When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments [55.19252983108372]
  We have developed a multi-agent AI system called StockAgent, driven by LLMs. The StockAgent allows users to evaluate the impact of different external factors on investor trading. It avoids the test set leakage issue present in existing trading simulation systems based on AI Agents.
  arXiv  Detail & Related papers  (2024-07-15T06:49:30Z)
• Startup success prediction and VC portfolio simulation using CrunchBase data [1.7897779505837144]
  This paper focuses on startups at their Series B and Series C investment stages, aiming to predict key success milestones. We introduce novel deep learning model for predicting startup success, integrating a variety of factors such as funding metrics, founder features, industry category. Our work demonstrates the considerable promise of deep learning models and alternative unstructured data in predicting startup success.
  arXiv  Detail & Related papers  (2023-09-27T10:22:37Z)
• Finding General Equilibria in Many-Agent Economic Simulations Using Deep Reinforcement Learning [72.23843557783533]
  We show that deep reinforcement learning can discover stable solutions that are epsilon-Nash equilibria for a meta-game over agent types. Our approach is more flexible and does not need unrealistic assumptions, e.g., market clearing. We demonstrate our approach in real-business-cycle models, a representative family of DGE models, with 100 worker-consumers, 10 firms, and a government who taxes and redistributes.
  arXiv  Detail & Related papers  (2022-01-03T17:00:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.