SLM-MATRIX: a multi-agent trajectory reasoning and verification framework for enhancing language models in materials data extraction

Li X., Huang Z., Quan S., Peng C., Ma X.

npj Computational Materials, vol.11, no.1, 2025 (SCI-Expanded, Scopus) identifier

  • Publication Type: Article / Article
  • Volume: 11 Issue: 1
  • Publication Date: 2025
  • Doi Number: 10.1038/s41524-025-01719-x
  • Journal Name: npj Computational Materials
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Ankara Haci Bayram Veli University Affiliated: No

Abstract

Small Language Models offer an efficient alternative for structured information extraction. We present SLM-MATRIX, a multi-path collaborative reasoning and verification framework based on SLMs, designed to extract material names, numerical values, and physical units from materials science literature. The framework integrates three complementary reasoning paths: a multi-agent collaborative path, a generator–discriminator path, and a dual cross-verification path. SLM-MATRIX achieves an accuracy of 92.85% on the BulkModulus dataset and reaches 77.68% accuracy on the MatSynTriplet dataset, both outperforming conventional methods and single-path models. Moreover, experiments on general reasoning benchmarks such as GSM8K and SVAMP validate the framework’s strong generalization capability. Ablation studies evaluate the effects of agent number, Mixture-of-Agents (MoA) depth, and discriminator design on overall performance. Overall, SLM-MATRIX presents an effective approach for high-quality material information extraction in resource-constrained and offers new insights into structured scientific text understanding tasks.