Large language models (LLMs) can already identify patterns and reason effectively, yet their variable accuracy hampers adoption in high-stakes decision-making applications. In this paper, we study this issue from a venture capital perspective by predicting idea-stage startup success based on founder traits. (i) To build a reliable prediction model, we introduce LLM-AR, a pipeline inspired by neural-symbolic systems that distils LLM-generated heuristics into probabilistic rules executed by the ProbLog automated-reasoning engine. (ii) An iterative policy-evolution loop incorporates association-rule mining to progressively refine the prediction rules. On unseen folds, LLM-AR achieves 59.5% precision and 8.7% recall, 5.9x the random baseline precision, while exposing every decision path for human inspection. The framework is interpretable and tunable via hyperparameters, showing promise to extend into other domains.
@article{arxiv.2510.22034,
title = {LLM-AR: LLM-powered Automated Reasoning Framework},
author = {Rick Chen and Joseph Ternasky and Aaron Ontoyin Yin and Xianling Mu and Fuat Alican and Yigit Ihlamur},
journal= {arXiv preprint arXiv:2510.22034},
year = {2025}
}