SLM-MATRIX: a multi-agent trajectory reasoning and verification framework for enhancing language models in materials data extraction
npj Computational Materials, cilt.11, sa.1, 2025 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 11 Sayı: 1
- Basım Tarihi: 2025
- Doi Numarası: 10.1038/s41524-025-01719-x
- Dergi Adı: npj Computational Materials
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
- Ankara Hacı Bayram Veli Üniversitesi Adresli: Hayır
Özet
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.