From Experiments to Expertise: Scientific Knowledge Consolidation for AI-Driven Computational Research

TL;DR

This paper introduces QMatSuite, a platform that consolidates scientific knowledge in AI-driven computational research, significantly reducing reasoning time and improving accuracy in quantum-mechanical simulations.

Contribution

QMatSuite enables knowledge accumulation, retrieval, and reflection in AI agents, bridging the gap between isolated simulations and expert scientific reasoning.

Findings

Reduces reasoning overhead by 67%

Improves simulation accuracy from 47% to 3% deviation

Achieves 1% deviation with zero pipeline failures on new materials

Abstract

While large language models (LLMs) have transformed AI agents into proficient executors of computational materials science, performing a hundred simulations does not make a researcher. What distinguishes research from routine execution is the progressive accumulation of knowledge -- learning which approaches fail, recognizing patterns across systems, and applying understanding to new problems. However, the prevailing paradigm in AI-driven computational science treats each execution in isolation, largely discarding hard-won insights between runs. Here we present QMatSuite, an open-source platform closing this gap. Agents record findings with full provenance, retrieve knowledge before new calculations, and in dedicated reflection sessions correct erroneous findings and synthesize observations into cross-compound patterns. In benchmarks on a six-step quantum-mechanical simulation workflow, accumulated knowledge reduces reasoning overhead by 67% and improves accuracy from 47% to 3% deviation from literature -- and when transferred to an unfamiliar material, achieves 1% deviation with zero pipeline failures.