MDAgent: A Modular Multi-Agent Framework for Autonomous Protein-Ligand Molecular Dynamics Simulations

Salomé Guilbert, Cassandra Masschelein, Jeremy Goumaz, Bohdan Naida, Philippe Schwaller

Keywords: molecular dynamics, large language models, automation, protein-ligand complexes

Abstract: Molecular dynamics (MD) simulations are indispensable for probing the structure, dynamics, and functions of biomolecular systems, including proteins and protein–ligand complexes. Despite their broad utility in drug discovery and protein engineering, the technical complexity of MD setup—encompassing parameterization, input preparation, and software configuration—remains a major barrier for widespread and efficient usage. Agentic LLMs have demonstrated their capacity to autonomously execute multi-step scientific processes, and to date, they have not successfully been used to automate protein-ligand MD workflows. Here, we present MDAgent, a modular multi-agent framework that autonomously designs and executes complete MD workflows for both protein and protein–ligand systems. The framework integrates dynamic tool use, retrieval-augmented parameter selection, and self-correcting behavior. MDAgent comprises three specialized agents, interacting to in turn plan the experiment, perform the simulation, and analyze the results. We evaluated its performance across eight benchmark systems of varying complexity, assessing success rate, efficiency, and adaptability. MDAgent reliably performed full MD simulations, corrected runtime errors through iterative reasoning, and produced meaningful analyses of protein–ligand interactions. This automated framework paves the way toward standardized, scalable, and time-efficient molecular modeling pipelines for future biomolecular and drug design applications.

Release To Public: Yes, please release this paper to the public

Submission Number: 30