ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal Packing

TL;DR

ColPackAgent is an agent framework that autonomously executes colloidal packing Monte Carlo simulations using a structured workflow, integrating domain-specific tools and LLMs for research automation.

Contribution

It introduces a novel agent system that combines a Python package, MCP server, and agent skill to automate complex colloidal packing simulations.

Findings

Successfully demonstrated autonomous and interactive simulation workflows.

Compared LLM performance in following structured simulation stages.

Showcased diverse colloidal packing examples with different particle types.

Abstract

We introduce ColPackAgent, an agent framework that autonomously runs Monte Carlo simulations of colloidal packing through a Model Context Protocol (MCP) tool server and an agent skill, whether as a standalone agent or inside an existing agent system. By harnessing the MCP server and agent skill, ColPackAgent executes a structured workflow for colloidal packing simulations, which are central to studies of phase behavior, self-assembly, and materials design. Without dedicated simulation tools and workflow instructions, general-purpose Large Language Model (LLM) agents tend to describe such workflows rather than execute them reliably. The MCP server exposes a custom-built colpack Python package that wraps HOOMD-blue hard-particle Monte Carlo, and the skill encodes a four-stage workflow contract. ColPackAgent can carry out the workflow interactively with human feedback, autonomously from an end-to-end prompt, or as autoresearch following a provided program file. We demonstrate the system in different modes with several colloidal packing simulation examples such as cube particles in 3D, a binary system of disks and capsules in 2D, and the 2D hard-disk freezing transition using autoresearch. We also compare model performance on this workflow across a panel of LLMs with 17 stage-specific prompts. This benchmark provides a stage-level check of how reliably different models follow the setup, planning, and analysis workflow. Together, these results show that pairing a domain Python package with MCP tools and a portable agent skill provides a practical route for turning a simulation toolkit into an agent-assisted research workflow.