Most venture capital (VC) investments fail, while a few deliver outsized returns. Accurately predicting startup success requires synthesizing complex relational evidence, including company disclosures, investor track records, and investment network structures, through explicit reasoning to form coherent, interpretable investment theses. Traditional machine learning and graph neural networks both lack this reasoning capability. Large language models (LLMs) offer strong reasoning but face a modality mismatch with graphs. Recent graph-LLM methods target in-graph tasks where answers lie within the graph, whereas VC prediction is off-graph: the target exists outside the network. The core challenge is selecting graph paths that maximize predictor performance on an external objective while enabling step-by-step reasoning. We present MIRAGE-VC, a multi-perspective retrieval-augmented generation framework that addresses two obstacles: path explosion (thousands of candidate paths overwhelm LLM context) and heterogeneous evidence fusion (different startups need different analytical emphasis). Our information-gain-driven path retriever iteratively selects high-value neighbors, distilling investment networks into compact chains for explicit reasoning. A multi-agent architecture integrates three evidence streams via a learnable gating mechanism based on company attributes. Under strict anti-leakage controls, MIRAGE-VC achieves +5.0% F1 and +16.6% PrecisionAt5, and sheds light on other off-graph prediction tasks such as recommendation and risk assessment. Code: https://anonymous.4open.science/r/MIRAGE-VC-323F.

翻译：多数风险投资（VC）以失败告终，而少数项目却能带来超额回报。准确预测初创企业的成功需要通过对复杂关系证据（包括公司披露信息、投资者历史业绩和投资网络结构）进行显式推理，以形成连贯、可解释的投资逻辑。传统机器学习与图神经网络均缺乏此类推理能力。大语言模型（LLMs）虽具备强大推理能力，却面临与图结构的模态失配问题。现有图-LLM方法主要针对答案存在于图内部的“图内任务”，而VC预测属于“图外任务”：预测目标位于网络外部。核心挑战在于选择能够最大化外部目标预测性能，同时支持逐步推理的图路径。本文提出MIRAGE-VC——一种多视角检索增强生成框架，旨在解决两大障碍：路径爆炸（数千条候选路径超出LLM上下文容量）与异质证据融合（不同初创企业需侧重不同分析维度）。我们基于信息增益的路径检索器通过迭代选择高价值邻接节点，将投资网络蒸馏为紧凑的推理链条。多智能体架构通过可学习的门控机制（依据公司属性动态调整）整合三条证据流。在严格的反信息泄露控制下，MIRAGE-VC实现了F1值提升5.0%、PrecisionAt5提升16.6%的显著效果，并为推荐系统、风险评估等其他图外预测任务提供了方法论启示。代码地址：https://anonymous.4open.science/r/MIRAGE-VC-323F。