# Agentic programs: an emerging form of scientific software in computational materials science

arXiv: https://arxiv.org/abs/2609.00795 · HTML: https://mlsanity.com/paper/2609.00795/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 1 Sep 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, 9 of 9)

- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [BLADE: Benchmarking Language Model Agents for Data-Driven Science](https://mlsanity.com/paper/2408.09667/) (2024)
- [El Agente: An Autonomous Agent for Quantum Chemistry](https://mlsanity.com/paper/2505.02484/) (2025)
- [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025)
- [SciSciGPT: Advancing Human-AI Collaboration in the Science of Science](https://mlsanity.com/paper/2504.05559/) (2025)
- [AiiDA: Automated Interactive Infrastructure and Database for Computational Science](https://mlsanity.com/paper/1504.01163/) (2015)
- [Human-In-the-Loop for Bayesian Autonomous Materials Phase Mapping](https://mlsanity.com/paper/2306.10406/) (2023)
- [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026)

## Abstract (arXiv)

Computational materials science has traditionally delegated algorithmic tasks to computers while leaving scientific judgments to humans. We argue that recent LLM-based agent harnesses enable an emerging form of scientific software, agentic programs, that combine deterministic algorithms with bounded LLM-based judgment, task-specific verification, episodic maturation, and complete delegation in production. We illustrate this concept with DeMARS, an agentic program for constructing atomistic models from experimentally measured disordered crystal structures.