Year: 2026
Type: conference-paper
Abstract: Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from firstprinciples physics.Designing an MD pipeline for a new system requires substantial expert knowledge: running it on even one molecule is expensive, ruling out trial-and-error.We automate this expert pipeline-design process with an LLM agent.Unlike existing MD agents that orchestrate a predefined tool set, we treat pipeline design as open-ended code generation in which the agent's behavior is reshaped online by verbal reward.Specifically, we build MDForge, an LLM agent whose in-context update rule densifies the sparse reward via a multiagent debate among physics experts.On three SAMPL host-guest binding free-energy benchmarks (CB[7], OAH, CBClip), MDForge automatically designs MD pipelines competitive with human experts.Deployed on a library of unseen candidate guests, its CB[7] pipeline discovers a novel binder that wet-lab competition NMR confirms is a high-affinity, picomolar CB[7] binder (K a ≈ 8 × 10 12 M -1 ).Our data and code are available at https: //github.com/Zehong-Wang/MDForge.
Institutions: University of Notre Dame, University of Connecticut
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7164589057