Skip to content
DraconiticResearch
Search Sources API
197,787 studies31 sourcesUpdated just now
Peer-reviewedCC BY-NC-NDChem

El Agente Quntur: A research collaborator agent for quantum chemistry

  • Juan B. Pérez-Sánchez1,2
  • Yunheng Zou1,2
  • Jorge A. Campos-Gonzalez-Angulo1,2
  • Marcel Müller1,2
  • Ignacio Gustín1
  • Andrew Wang1,2
  • Han Hao3
  • Tsz Wai Ko1,2
  • Changhyeok Choi1,2
  • Eric S. Isbrandt3
  • Mohammad Ghazi Vakili1,4,2
  • Hanyong Xu1
3 more authors
  • Chris Crebolder3,4
  • Varinia Bernales5,4
  • Alán Aspuru‐Guzik
5 affiliations
  1. 1Department of Chemistry, University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada
  2. 2Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON M5G 0C6, Canada
  3. 3Acceleration Consortium, 700 University Ave., Toronto, ON M7A 2S4, Canada
  4. 4Department of Computer Science, University of Toronto, 40 St. George St., Toronto, ON M5S 2E4, Canada
  5. 5Canadian Institute for Advanced Research (CIFAR), 661 University Ave., Toronto, ON M5G 1M1, Canada
Open at sourcePDFDOICite

Abstract

Quantum chemistry is a foundational tool for chemistry, materials science, computational biology, and others. Despite its power, its application remains restricted to experts due to methodological complexity, software heterogeneity, and the need for informed interpretation. To bridge this accessibility gap, we introduce El Agente Quntur, a hierarchical, multi-agent system designed as a research collaborator for computational quantum chemistry. Quntur follows three strategies: (1) reasoning-driven decisions rather than hard-coded procedural policies, (2) general and composable actions, and (3) guided deep research integration of quantum-chemical reasoning with software logic and syntax. Instantiated in ORCA, Quntur reasons over software documentation and literature to plan, execute, adapt, and analyze in silico chemistry experiments. Benchmarking against Claude Code in the same software environment shows that Quntur's domain-specific agent architecture more faithfully translates open-ended chemical requests into defensible end-to-end computational protocols. We outline advances, bottlenecks, and a roadmap toward an autonomous end-to-end computational chemistry research agent.

Related

  1. El Agente Quntur: Agentic Active-Space Selection for CASSCF
    Juan B. Pérez-Sánchez, Viviana Roman-Ventura, Olalla Nieto-Faza +3
    arXivPreprintarXiv licenceFull textPhysical chemistryarXiv
  2. StudDFT: A quantum chemistry program for educational and research purposes
    Stanislav K. Ignatov
    arXivPreprintarXiv licenceFull textPhysical chemistryarXiv
  3. Open Ontology of Polymer Chemistry: Accumulation and Self-Improving Memory Mechanisms for Polymer Research
    Brett M. Savoie
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  4. Essential Oil-Containing Mouthrinses for Plaque and Gingivitis Control: Formulation Chemistry, Human Salivary Biomarkers, Mechanistic Evidence, and Research Priorities
    Molecules (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral chemistryEurope PMC
  5. How do the research evaluation requirements of Chinese universities, which are oriented towards paper publication, affect the development of chemistry graduate students and faculty members?
    xingyu zhu
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@article{perezsanchez2026agente,
  title = {{El Agente Quntur: A research collaborator agent for quantum chemistry}},
  author = {Juan B. Pérez-Sánchez and Yunheng Zou and Jorge A. Campos-Gonzalez-Angulo and Marcel Müller and Ignacio Gustín and Andrew Wang and Han Hao and Tsz Wai Ko and Changhyeok Choi and Eric S. Isbrandt and Mohammad Ghazi Vakili and Hanyong Xu and Chris Crebolder and Varinia Bernales and Alán Aspuru‐Guzik},
  journal = {Chem},
  year = {2026},
  month = sep,
  doi = {10.1016/j.chempr.2026.103259},
  url = {https://doi.org/10.1016/j.chempr.2026.103259},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - El Agente Quntur: A research collaborator agent for quantum chemistry
AU  - Juan B. Pérez-Sánchez
AU  - Yunheng Zou
AU  - Jorge A. Campos-Gonzalez-Angulo
AU  - Marcel Müller
AU  - Ignacio Gustín
AU  - Andrew Wang
AU  - Han Hao
AU  - Tsz Wai Ko
AU  - Changhyeok Choi
AU  - Eric S. Isbrandt
AU  - Mohammad Ghazi Vakili
AU  - Hanyong Xu
AU  - Chris Crebolder
AU  - Varinia Bernales
AU  - Alán Aspuru‐Guzik
PY  - 2026
DA  - 2026/09/01
JO  - Chem
DO  - 10.1016/j.chempr.2026.103259
UR  - https://doi.org/10.1016/j.chempr.2026.103259
AB  - Quantum chemistry is a foundational tool for chemistry, materials science, computational biology, and others. Despite its power, its application remains restricted to experts due to methodological complexity, software heterogeneity, and the need for informed interpretation. To bridge this accessibility gap, we introduce El Agente Quntur, a hierarchical, multi-agent system designed as a research collaborator for computational quantum chemistry. Quntur follows three strategies: (1) reasoning-driven decisions rather than hard-coded procedural policies, (2) general and composable actions, and (3) guided deep research integration of quantum-chemical reasoning with software logic and syntax. Instantiated in ORCA, Quntur reasons over software documentation and literature to plan, execute, adapt, and analyze in silico chemistry experiments. Benchmarking against Claude Code in the same software environment shows that Quntur's domain-specific agent architecture more faithfully translates open-ended chemical requests into defensible end-to-end computational protocols. We outline advances, bottlenecks, and a roadmap toward an autonomous end-to-end computational chemistry research agent.
SN  - 2451-9294
SN  - 2451-9308
ER  -