SLM-MATRIX: a multi-agent trajectory reasoning and verification framework for enhancing language models in materials data extraction
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 l...
Saved in:
| Main Authors: | Xin Li, Zhixuan Huang, Shu Quan, Cheng Peng, Xiaoming Ma |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-025-01719-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
CoReaAgents: A Collaboration and Reasoning Framework Based on LLM-Powered Agents for Complex Reasoning Tasks
by: Zhonghe Han, et al.
Published: (2025-05-01) -
Friction Performance Analysis of WC-Reinforced IN718 Composite Material Based on SLM Process
by: Xuejin Zhao, et al.
Published: (2024-11-01) -
Track trajectory, molten pool and defect characterization in NiTi single-track selective laser melting (SLM) experiments
by: Peiyu Dong, et al.
Published: (2024-11-01) -
Divide and summarize: improve SLM text summarization
by: Alexandre Bailly, et al.
Published: (2025-08-01) -
SLM-printed EUROFER steel for fusion applications
by: Ramil Gaisin, et al.
Published: (2025-06-01)