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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xiangru, Jiang, Zekun, Yang, Heng, Tan, Cheng, Lan, Xingying, Xu, Chunming, Zhou, Tianhang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908654414856192
author Wang, Xiangru
Jiang, Zekun
Yang, Heng
Tan, Cheng
Lan, Xingying
Xu, Chunming
Zhou, Tianhang
author_facet Wang, Xiangru
Jiang, Zekun
Yang, Heng
Tan, Cheng
Lan, Xingying
Xu, Chunming
Zhou, Tianhang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11769
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules
Wang, Xiangru
Jiang, Zekun
Yang, Heng
Tan, Cheng
Lan, Xingying
Xu, Chunming
Zhou, Tianhang
Chemical Physics
Machine Learning
Quantitative Methods
Methodology
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.
title Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules
topic Chemical Physics
Machine Learning
Quantitative Methods
Methodology
url https://arxiv.org/abs/2511.11769