A collaborative agent with two lightweight synergistic models for autonomous crystal materials research
Summary
Nature Machine Intelligence, Published online: 10 September 2026; doi:10.1038/s42256-026-01298-6 Shi et al. demonstrate a dual architecture approach for materials research, integrating two lightweight large language models for collaborative reasoning and scientific tool execution. The method achieves competitive performance while remaining affordable and locally deployable.
Evidence & checks
- Discovery channel
- Nature Portfolio · Nature Machine Intelligence
- Original material
- www.nature.com
- Material type
- Source page; material type not verified
- Material basis
- Source excerpt
- Review status
- No human-review record