paper-with-me

홈 › Papers

MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback

2026-06-11 · Zehong Wang, Yijun Ma, Connor R. Schmidt, Tianyi Ma, Weixiang Sun, Ziming Li, Xiaoguang Guo, Chuxu Zhang, Matthew J. Webber, Yanfang Ye arxiv

Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle 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 multi-agent debate among physics experts. On three SAMPL host-guest binding free-energy benchmarks, 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. Our data and code are available at https://github.com/Zehong-Wang/MDForge.

📄 PDF Abstract BibTeX arXiv:2606.12916

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations

2025-12-10 · Salomé Guilbert, Cassandra Masschelein, Jeremy Goumaz, Bohdan Naida 외 arxiv

Force field-based 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 uti…

Drug Discovery

Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model

2025-02-14 · Bo Ni, Markus J. Buehler

Proteins are dynamic molecular machines whose biological functions, spanning enzymatic catalysis, signal transduction, and structural adaptation, are intrinsically linked to their motions. Designing proteins with targete…

Protein Design

Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis

2026-01-25 · Hao Li, He Cao, Shenyao Peng, Zijing Liu 외 arxiv

Language models are revolutionizing the biochemistry domain, assisting scientists in drug design and chemical synthesis with high efficiency. Yet current approaches struggle between small language models prone to halluci…

Reinforcement LearningInformation Retrieval

MDCrow: Automating Molecular Dynamics Workflows with Large Language Models

2025-02-13 · Quintina Campbell, Sam Cox, Jorge Medina, Brittany Watterson 외

Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLM) have demonstrated success in automating complex …

MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization

2025-12-23 · Zhuo Yang, Yeyun Chen, Jiaqing Xie, Ben Gao 외 arxiv

Molecular editing and optimization are multi-step problems that require iteratively improving properties while keeping molecules chemically valid and structurally similar. We frame both tasks as sequential, tool-guided d…

Reinforcement Learning