# Agent-MD: Selective LLM Intervention with Event-Driven Escalation for Stateful GCMC--MD Campaigns

arXiv: https://arxiv.org/abs/2608.07637 · HTML: https://mlsanity.com/paper/2608.07637/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 5 of 5)

- [AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance](https://mlsanity.com/paper/2003.12476/) (2020)
- [MDCrow: Automating Molecular Dynamics Workflows with Large Language Models](https://mlsanity.com/paper/2502.09565/) (2025)
- [AiiDA: Automated Interactive Infrastructure and Database for Computational Science](https://mlsanity.com/paper/1504.01163/) (2015)
- [SimMOF: AI agent for Automated MOF Simulations](https://mlsanity.com/paper/2603.29152/) (2026)
- [Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System](https://mlsanity.com/paper/2604.07681/) (2026)

## Built on by (most cited first, 2 of 2)

- [Science Done on a Machine by a Machine: AI Agents in Computational Chemistry](https://mlsanity.com/paper/2608.18508/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Long-running molecular simulation campaigns require repeated continuation from saved states, provenance-aware progression, adaptive assessment, and occasional interpretation of workflow conditions that cannot be resolved safely by fixed rules. Here, we present Agent-MD, a framework that places large language model (LLM) reasoning selectively at campaign construction and event-triggered review, while routine simulation, analysis, continuation, archiving, and state progression are handled by a persistent rule-based campaign agent using approved policies and explicit state records. Agent-MD was demonstrated in a grand canonical Monte Carlo-molecular dynamics (GCMC-MD) water-vapor desorption campaign comprising five montmorillonite systems and three sequential relative-humidity states (RH = 0.9-0.3-0.1). Across 15 system-RH states, the workflow completed 120 segmented simulation cycles with state-specific sampling lengths and provenance-aware restart inheritance. Routine production required no live reasoning-agent invocation, while one state reached a review boundary; two preserved incidents were subsequently evaluated through blinded reasoning-agent replay, which identified the underlying workflow problems and recommended appropriate follow-up actions. The simulations also revealed distinct composition-dependent low-RH responses, with Ca-bearing montmorillonite retaining more interlayer water and maintaining a larger basal spacing than the Na- and K-bearing systems, while the highest-charge Na system retained more residual water under dry conditions. These results demonstrate that long-running scientific workflows need not place every operation inside an LLM reasoning loop: selective reasoning can instead be combined with deterministic execution, structured evidence, and validated control handoffs to provide reproducible and auditable agent-assisted molecular simulation.