A Multi-Agent Framework for Automated Coarse-Grained Molecular Dynamics of Polymers

CGMas, a multi-agent framework developed by researchers, automates coarse-grained molecular dynamics of polymers from a natural-language specification, completing all 27 homopolymer and copolymer tasks, matching atomistic density within 5% in 22 cases, and reducing simulation time from 38-88 minutes to 1 minute. The framework uses a large-language-model reasoning agent to infer atomistic topology and layered self-correction to resolve physical errors, establishing agentic LLMs as a route to automated polymer coarse-graining.

arXiv:2608.06694v1 Announce Type: new Abstract: Coarse-grained CG molecular dynamics extends polymer simulation beyond the scales accessible to all-atom AA methods, but bottom-up CG modeling is laborious. The CG resolution is a design choice, so a transferable parameter set is generally not available and the potentials are derived anew for each polymer mapping. Here we present CGMas, a multi-agent framework that automates topology construction, equilibration, mapping, potential derivation, and validation from a natural-language specification of the polymer and target resolution. A large-language-model LLM reasoning agent infers the AA topology from polymer name, while layered self-correction resolves physical errors common to unsaturated, heteroatom-containing, and polar polymers. Downstream agents equilibrate the system, map it onto CG representation, derive potentials through Boltzmann inversion, and benchmark the model against its atomistic reference. CGMas completed all 27 homopolymer and copolymer tasks, matched the AA density to within 5% in 22, and reduced simulation from 38-88 min to 1 min, establishing agentic LLMs as a route to automated polymer coarse-graining.