ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal Packing
ColPackAgent is a new framework designed to autonomously run Monte Carlo simulations for colloidal packing. It utilizes a Model Context Protocol tool server and an agent skill to execute structured workflows. The system has been demonstrated in various simulation scenarios, showcasing its effectiveness in research workflows.
- ▪ColPackAgent autonomously runs Monte Carlo simulations through a Model Context Protocol tool server.
- ▪The framework can operate as a standalone agent or within an existing agent system.
- ▪It has been tested with different colloidal packing simulation examples, including 3D cube particles and 2D hard-disk freezing transitions.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.15625 (cs) [Submitted on 15 May 2026] Title:ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal Packing Authors:Lijie Ding, Changwoo Do View a PDF of the paper titled ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal Packing, by Lijie Ding and 1 other authors View PDF HTML (experimental) 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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
