Metraipolis › archive › dc_7e169617ef16

Can Autonomous LLM Agents Execute Multireference Quantum Chemistry Calculations? — arXiv:2609.13357

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13357
License (as archived)
CC0-1.0
Archived
2026-10-16T02:38:37.344Z
SHA-256 of the archived text
10509ede725acb94e5d07e5c47d834f49dca1ff72d524877acedea0c2ce8a7b8
Stable URL of this page
https://metraipolis.com/documento/dc_7e169617ef16

How to cite

Can Autonomous LLM Agents Execute Multireference Quantum Chemistry Calculations? — arXiv:2609.13357 — arXiv (en), https://arxiv.org/abs/2609.13357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e169617ef16 (Metraipolis archive dc_7e169617ef16, sha256 10509ede725acb94e5d07e5c47d834f49dca1ff72d524877acedea0c2ce8a7b8)
BibTeX
@misc{dc7e169617ef16,
  title = {Can Autonomous LLM Agents Execute Multireference Quantum Chemistry Calculations? — arXiv:2609.13357},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13357},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e169617ef16; sha256 10509ede725acb94e5d07e5c47d834f49dca1ff72d524877acedea0c2ce8a7b8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-15 in physics.comp-ph).
Categorie arXiv: Chemical Physics (physics.chem-ph) ; Materials Science (cond-mat.mtrl-sci); Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.13357 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:24:17.076Z dalla pagina https://arxiv.org/catchup/physics.comp-ph/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).