{"type":"ScholarlyArticle","title":"Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agents","authors":[{"name":"Zhongyang Liu","slug":"zhongyang-liu","given":"Zhongyang","family":"Liu","affiliation":""},{"name":"Haoyu Pei","slug":"haoyu-pei","given":"Haoyu","family":"Pei","affiliation":""},{"name":"Xiangyi Xiao","slug":"xiangyi-xiao","given":"Xiangyi","family":"Xiao","affiliation":""},{"name":"Xiaocong Du","slug":"xiaocong-du","given":"Xiaocong","family":"Du","affiliation":""},{"name":"Yihui Li","slug":"yihui-li","given":"Yihui","family":"Li","affiliation":""},{"name":"Suting Hong","slug":"suting-hong","given":"Suting","family":"Hong","affiliation":""},{"name":"Kunpeng Zhang","slug":"kunpeng-zhang","given":"Kunpeng","family":"Zhang","affiliation":""},{"name":"Haipeng Zhang","slug":"haipeng-zhang","given":"Haipeng","family":"Zhang","affiliation":""}],"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.\r\nUsing 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.","doi":"10.24963/ijcai.2026/721","url":"https://ijcai.org/proceedings/2026/721","pdf":"https://ijcai.org/proceedings/2026/0721.pdf","markdown":"https://ijcai.org/proceedings/2026/721.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/721","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI4Tech: AI Enabling Technologies","track":"AI4Tech: AI Enabling Technologies","number":721,"pages":{"first":6480,"last":6490},"keywords":["Domain-specific AI4Tech: AI4Finance"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}