The Gaining Paths to Investment Success: Information-Driven LLM Graph Reasoning for Venture Capital Prediction

TL;DR

This paper introduces MIRAGE-VC, a novel framework that enhances venture capital prediction by explicitly reasoning over complex investment networks using an information-gain-driven, multi-path retrieval approach with LLMs.

Contribution

It proposes MIRAGE-VC, a new method combining retrieval-augmented generation and multi-agent evidence fusion to improve off-graph prediction tasks like VC success prediction.

Findings

Achieved +5.0% F1 score improvement

Achieved +16.6% Precision@5

Effectively handles path explosion and heterogeneous evidence fusion

Abstract

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.