ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulations

2025-10-13

AI Summary

High barriers and complex workflows hinder widespread adoption of coarse-grained molecular dynamics (CG-MD) simulations for polymers. Method: We propose the first natural-language-driven, multi-agent AI framework tailored for topological polymers, integrating large language models (LLMs) with domain-specific tools (e.g., LAMMPS). It comprises four coordinated agents—Config, Simulation, Report, and Workflow—supporting interactive and autonomous simulation of linear, cyclic, brush, star, and dendritic polymer architectures. Contribution/Results: The framework enables end-to-end automation—from natural-language instructions to configuration generation, simulation execution, analysis, and report generation—with iterative user feedback. Experimental validation demonstrates robust conformational modeling across solvent environments, temperature conditions, and parameter spaces. It autonomously uncovers key structure–property relationships: (i) how interaction parameters govern linear chain conformations, and (ii) how grafting density modulates the persistence length of brush polymers—advancing AI-driven materials discovery.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We introduce ToPolyAgent, a multi-agent AI framework for performing coarse-grained molecular dynamics (MD) simulations of topological polymers through natural language instructions. By integrating large language models (LLMs) with domain-specific computational tools, ToPolyAgent supports both interactive and autonomous simulation workflows across diverse polymer architectures, including linear, ring, brush, and star polymers, as well as dendrimers. The system consists of four LLM-powered agents: a Config Agent for generating initial polymer-solvent configurations, a Simulation Agent for executing LAMMPS-based MD simulations and conformational analyses, a Report Agent for compiling markdown reports, and a Workflow Agent for streamlined autonomous operations. Interactive mode incorporates user feedback loops for iterative refinements, while autonomous mode enables end-to-end task execution from detailed prompts. We demonstrate ToPolyAgent's versatility through case studies involving diverse polymer architectures under varying solvent condition, thermostats, and simulation lengths. Furthermore, we highlight its potential as a research assistant by directing it to investigate the effect of interaction parameters on the linear polymer conformation, and the influence of grafting density on the persistence length of the brush polymer. By coupling natural language interfaces with rigorous simulation tools, ToPolyAgent lowers barriers to complex computational workflows and advances AI-driven materials discovery in polymer science. It lays the foundation for autonomous and extensible multi-agent scientific research ecosystems.

Problem

• Simulating topological polymers using natural language instructions
• Integrating language models with computational tools for polymer studies
• Lowering barriers to complex polymer simulation workflows

Innovation

• Multi-agent AI framework for topological polymer simulations
• Integrates large language models with domain-specific computational tools
• Supports both interactive and autonomous simulation workflows