OpenAlex ·
Can Autonomous LLM Agents Execute Multireference Quantum Chemistry Calculations?
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2609.13357
- Original
- Read it at the publisher
- Topics
Abstract
Multireference electronic-structure calculations remain difficult to automate because critical workflow decisions, including active-space selection, state averaging, convergence recovery, and state identification, traditionally rely on expert judgment. Here, we investigate whether an autonomous large language model (LLM) agent can perform these tasks without human intervention. The agent selects active spaces using literature-grounded analogies or explicitly documented chemical reasoning, generates and submits ORCA calculations, analyzes outputs, and records all decisions in an auditable reasoning log. Benchmarking against 558 vertical transition energies (VTEs) from QUESTDB shows that an unguided baseline agent achieves 24.9% coverage with a mean absolute error (MAE) of 0.373 eV. Introducing a structured decision ladder increases coverage to 44.1% while reducing the MAE to 0.339 eV. The largest gains are observed for double and Rydberg excitations, demonstrating that expert-informed procedural guidance substantially improves active-space construction and state identification. When provided with complete workflow information, the agent successfully reproduces published QUEST calculations with an MAE of only 23 meV, resolving 75% of target configurations within seven attempts. These results demonstrate that contemporary LLM agents can autonomously execute and reproduce complex multireference quantum-chemical workflows, while highlighting the importance of structured reasoning frameworks for achieving reliable high-throughput and high-fidelity electronic-structure calculations.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Materials Science
ALIGNN 2.0: A Unified Line-Graph Neural Network Framework for Materials Screening, Force Fields, Inverse Design, Spectroscopy, and Microscopy
ADMET-EvO: a self-evolving scientific agent for sustained research across heterogeneous tasks
Human Language Shapes the Emerging Physical Reasoning in Large Language Models
Predicting directional flexibility in proteins
Orbital-Free Surrogate Functionals Yield Transferable Interatomic Potentials and Electron Densities
Get the few papers worth your time in Materials Science every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.