EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Differentiated memory and scientific cognition in AI research agents

Diego F Cuadros, Abdoul-Aziz Maiga, Sid Thatham, Alvaro Ortiz, Margaret Powers-Fletcher, Ming Tang

Frontiers in Big Data · 05.08.2026 · 9

DOI: 10.3389/fdata.2026.1916523 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Big Data, online erschienen am 05.08.2026. Verfasst von Diego F Cuadros und 5 weiteren Autor:innen. Beteiligte Einrichtung: Digital Epidemiology Laboratory, Digital Futures, University of Cincinnati, Cincinnati, OH, United States. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AI research agents increasingly support ideation, literature search, coding, experimental execution, analysis, and manuscript drafting across the scientific workflow. This progress advances automated discovery, but workflow automation is not scientific cognition. Scientific reasoning is cumulative and path-dependent: it depends on what a researcher has written, read, learned from critique, absorbed through experience, and used as habitual standards for judging novelty, rigor, feasibility, and significance. We propose Mnemo as a framework for modeling scientific cognition in AI research agents. First, scientific cognition may require differentiated memory, organized into distinct spaces for authored work, external reference, critique, experience, and judgment. Second, provenance should be treated not as passive metadata but as memory routing, because source origin helps determine cognitive function in reasoning. Third, new ideas may be better modeled as controlled collisions across memory spaces, filtered by judgment, rejection, and epistemic calibration, than as generic recombination from model priors. Mnemo motivates a research agenda for AI in science centered on routing fidelity, critique use, judgment alignment, rejection quality, and epistemic calibration.

Schlagwörter

Stichwörter der Autor:innen

AI for scienceAI research agentscognitive architecturedifferentiated memorylarge language model agentsprovenancescientific cognitionscientific judgment

Autor:innen und Institutionen

  • Digital Epidemiology Laboratory, Digital Futures, University of Cincinnati, Cincinnati, OH, United States.
  • Department of Biological Sciences, University of Cincinnati, Cincinnati, OH, United States.
  • Center for Humanities and Technology (CHaT), University of Cincinnati, Cincinnati, OH, United States.
  • Norwegian University of Science and Technology, Trondheim, Norway.
  • UC Utilities, University of Cincinnati, Cincinnati, OH, United States.
  • Department of Mathematical Sciences, University of Cincinnati, Cincinnati, OH, United States.

Zitieren

APA

Cuadros, D. F., Maiga, A. A., Thatham, S., Ortiz, A., Powers-Fletcher, M., & Tang, M. (2026). Differentiated memory and scientific cognition in AI research agents. Frontiers in Big Data, 9. https://doi.org/10.3389/fdata.2026.1916523

Vancouver

Cuadros DF, Maiga AA, Thatham S, Ortiz A, Powers-Fletcher M, Tang M. Differentiated memory and scientific cognition in AI research agents. Frontiers in Big Data. 2026;9. doi:10.3389/fdata.2026.1916523

BibTeX
@article{Cuadros2026,
  author = {Cuadros, Diego F and Maiga, Abdoul-Aziz and Thatham, Sid and Ortiz, Alvaro and Powers-Fletcher, Margaret and Tang, Ming},
  title = {Differentiated memory and scientific cognition in AI research agents},
  journal = {Frontiers in Big Data},
  year = {2026},
  volume = {9},
  doi = {10.3389/fdata.2026.1916523}
}
Kostenlos starten →