Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules

TL;DR

Socrates-Mol is a novel framework that leverages language models as Bayesian reasoners for molecular property prediction, reducing fine-tuning needs and improving accuracy through self-consistency and empirical Bayesian methods.

Contribution

It introduces a self-oriented reasoning framework that transforms language models into Bayesian reasoners for molecules, addressing cold start issues without fine-tuning.

Findings

72% MAE reduction in LogP regression

112% R-squared improvement in regression tasks

Over 70% cost reduction compared to fine-tuning

Abstract

Molecular property prediction is fundamental to chemical engineering applications such as solvent screening. We present Socrates-Mol, a framework that transforms language models into empirical Bayesian reasoners through context engineering, addressing cold start problems without model fine-tuning. The system implements a reflective-prediction cycle where initial outputs serve as priors, retrieved molecular cases provide evidence, and refined predictions form posteriors, extracting reusable chemical rules from sparse data. We introduce ranking tasks aligned with industrial screening priorities and employ cross-model self-consistency across five language models to reduce variance. Experiments on amine solvent LogP prediction reveal task-dependent patterns: regression achieves 72% MAE reduction and 112% R-squared improvement through self-consistency, while ranking tasks show limited gains due to systematic multi-model biases. The framework reduces deployment costs by over 70% compared to full fine-tuning, providing a scalable solution for molecular property prediction while elucidating the task-adaptive nature of self-consistency mechanisms.