EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing LLM inference with human expert knowledge: a case study on multi-agent robotics fault diagnosis and prediction

Yongxu Ren, Felix Deichsel, Jürgen Seiler, André Kaup, Philipp Beckerle

Artificial Life and Robotics · 23.07.2026

DOI: 10.1007/s10015-026-01136-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Life and Robotics, online erschienen am 23.07.2026. Verfasst von Yongxu Ren und 4 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Friedrich-Alexander-Universität Erlangen-Nürnberg.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) can support predictive maintenance by reasoning over text-based expert knowledge, but their reliability depends on how such knowledge is structured and retrieved. This work presents an expert-knowledge-grounded LLM inference pipeline that combines Delphi- and FMEA-derived maintenance knowledge, retrieval-augmented prompting, and engineered telemetry summaries. In a multi-robot case study, we evaluate basic knowledge queries, complex diagnostic questions, and telemetry description tasks. Retrieved expert knowledge improves LLM-based diagnostic answers, while a deterministic knowledge-graph reasoner performs best on threshold-driven telemetry questions. The results indicate a complementary design in which graph inference provides traceable rule execution and expert-knowledge-grounded LLMs synthesize diagnostic explanations from selected evidence.

Förderung

  • Friedrich-Alexander-Universität Erlangen-Nürnberg

Zitieren

APA

Ren, Y., Deichsel, F., Seiler, J., Kaup, A., & Beckerle, P. (2026). Enhancing LLM inference with human expert knowledge: a case study on multi-agent robotics fault diagnosis and prediction. Artificial Life and Robotics. https://doi.org/10.1007/s10015-026-01136-3

Vancouver

Ren Y, Deichsel F, Seiler J, Kaup A, Beckerle P. Enhancing LLM inference with human expert knowledge: a case study on multi-agent robotics fault diagnosis and prediction. Artificial Life and Robotics. 2026. doi:10.1007/s10015-026-01136-3

BibTeX
@article{Ren2026,
  author = {Ren, Yongxu and Deichsel, Felix and Seiler, Jürgen and Kaup, André and Beckerle, Philipp},
  title = {Enhancing LLM inference with human expert knowledge: a case study on multi-agent robotics fault diagnosis and prediction},
  journal = {Artificial Life and Robotics},
  year = {2026},
  doi = {10.1007/s10015-026-01136-3}
}
Kostenlos starten →