Agentic programs: an emerging form of scientific software in computational materials science
On the map: LLM agents and tool use → Medical and scientific domain agents
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.
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.
Builds on
9 of 34 references.
Closest ancestors · 2
Same direction, newest first
- 2026Harnessing AtomisticSkills for Agentic Atomistic Research18 May
- 2025El Agente: An Autonomous Agent for Quantum Chemistry5 May
Other references · 7
- 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
- 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 356
- 2024BLADE: Benchmarking Language Model Agents for Data-Driven Sciencecited by 77
- 2025CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolutioncited by 34
- 2025SciSciGPT: Advancing Human-AI Collaboration in the Science of Sciencecited by 27
- 2015AiiDA: Automated Interactive Infrastructure and Database for Computational Sciencecited by 20
- 2023Human-In-the-Loop for Bayesian Autonomous Materials Phase Mappingcited by 10
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Towards Agentic Intelligence for Materials Science
- 2025Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists
- 2026Can Coding Agents Reproduce Findings in Computational Materials Science?
- 2026CompMat-Bench: Benchmarking AI Agents for Computational Materials Science
- 2025DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation
- 2025GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols
- 2025ChemGraph: An Agentic Framework for Computational Chemistry Workflows
- 2026From Data to Theory: Autonomous Large Language Model Agents for Materials Science