EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating the Theory of Inventive Problem Solving with Large Language Models: Enhancing Reasoning for Innovation in Materials Science at the Molecular Scale

Sergey Gusarov, Svetlana Sapelnikova, Julio J. Valdes, Anguang Hu, Stanislav R. Stoyanov

ChemEngineering · 21.04.2026 · 10 (4) · 54

DOI: 10.3390/chemengineering10040054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ChemEngineering, online erschienen am 21.04.2026. Verfasst von Sergey Gusarov und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Council Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work proposes a general conceptual framework for integrating TRIZ (Theory of Inventive Problem Solving) structured reasoning into large language model (LLM)-based workflows for chemical and materials science. We argue that persistent AI challenges in this domain—data scarcity, weak scaffold transferability, unphysical predictions, and limited interpretability—are most naturally framed as TRIZ-style contradictions and that embedding contradiction-resolution logic into LLM reasoning can elevate AI from pattern-matching to inventive, researcher-like problem solving. Unlike prior AI–TRIZ integrations such as AutoTRIZ and TRIZ-GPT, which address general engineering tasks, the present framework extends TRIZ tools to physicochemical phenomena and targets local, privacy-preserving deployment. To illustrate the concept and identify directions for further development, we implement and evaluate a simplified three-stage proof-of-concept pipeline on nine local LLMs across eleven chemical problems. Results show that the TRIZ-guided pipeline substantially reduces token consumption—both overall and especially in the solution-generation stage—without an obvious loss in solution quality under the adopted evaluation criteria, suggesting considerable room for further improvement as the framework matures.

Förderung

  • National Research Council Canada

Zitieren

APA

Gusarov, S., Sapelnikova, S., Valdes, J. J., Hu, A., & Stoyanov, S. R. (2026). Integrating the Theory of Inventive Problem Solving with Large Language Models: Enhancing Reasoning for Innovation in Materials Science at the Molecular Scale. ChemEngineering, 10(4), 54. https://doi.org/10.3390/chemengineering10040054

Vancouver

Gusarov S, Sapelnikova S, Valdes JJ, Hu A, Stoyanov SR. Integrating the Theory of Inventive Problem Solving with Large Language Models: Enhancing Reasoning for Innovation in Materials Science at the Molecular Scale. ChemEngineering. 2026;10(4):54. doi:10.3390/chemengineering10040054

BibTeX
@article{Gusarov2026,
  author = {Gusarov, Sergey and Sapelnikova, Svetlana and Valdes, Julio J. and Hu, Anguang and Stoyanov, Stanislav R.},
  title = {Integrating the Theory of Inventive Problem Solving with Large Language Models: Enhancing Reasoning for Innovation in Materials Science at the Molecular Scale},
  journal = {ChemEngineering},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {54},
  doi = {10.3390/chemengineering10040054}
}
Kostenlos starten →