El Agente Quntur
Purpose and distinctive contribution
Act as a computational research collaborator for quantum chemistry.
Hierarchical agents use documentation and literature to plan, execute, adapt and analyze ORCA calculations, emphasizing reasoning, composable actions and guided deep research.
This page describes the specific system in the cited study, not every capability of the wider El Agente platform.
Publication and full author credit
Juan B. Pérez-Sánchez; Yunheng Zou; Jorge A. Campos-Gonzalez-Angulo; Marcel Müller; Ignacio Gustin; Andrew Wang; Han Hao; Tsz Wai Ko; Changhyeok Choi; Eric S. Isbrandt; Mohammad Ghazi Vakili; Hanyong Xu; Chris Crebolder; Varinia Bernales; Alán Aspuru-Guzik. (2026). El Agente Quntur: A research collaborator agent for quantum chemistry. Chem, article 103259 (in press, corrected proof).
Publication or posting date: . Chem: available online 24 September 2026; publisher page labels In Press, Corrected Proof.
Preprint and version history →
The linked preprint has a version-specific author list: Juan B. Pérez-Sánchez; Yunheng Zou; Jorge A. Campos-Gonzalez-Angulo; Marcel Müller; Ignacio Gustin; Andrew Wang; Han Hao; Tsz Wai Ko; Changhyeok Choi; Eric S. Isbrandt; Mohammad Ghazi Vakili; Hanyong Xu; Chris Crebolder; Varinia Bernales; Alán Aspuru-Guzik. The journal citation above preserves the published author list.
Research roles and contributions
Author contributions J.B.P.S. and Y.Z. conceived the research, developed the software, designed and performed the benchmark and case-study evaluations, analyzed the results, and prepared the manuscript. J.A.C.G.A. contributed to the conceptual development of the research, tested the system, performed and evaluated benchmark and case-study executions, analyzed the results, and contributed to manuscript preparation. M.M., I.G., and A.W. tested the system, performed and evaluated benchmark and case-study executions, and contributed to manuscript preparation. H.H., T.W.K., Changhyeok Choi, and E.S.I. performed and evaluated benchmark and case-study executions. M.G.V., H.X., and Chris Crebolder maintained the system, contributed to software development and deployment, and supported the system’s availability during review. V.B. and A.A.-G. supervised the research. All authors reviewed and approved the final manuscript.
Software, artifacts, and limitations
Manuscript explicitly states source code is presently non-public.
Capabilities are bounded by the tasks, tools, models, and evaluation conditions reported in the study. No universal speedup, reliability, or fully autonomous experimental capability is claimed here. Consult the linked manuscript’s methods and limitations before applying its results to a new workflow.