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

Ren Y, Deichsel F, Seiler J, Kaup A, Beckerle P (2026)

Publication Type: Journal article

Publication year: 2026

Journal

DOI: 10.1007/s10015-026-01136-3

Abstract

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.

Authors with CRIS profile

How to cite

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

MLA:

Ren, Yongxu, et al. "Enhancing LLM inference with human expert knowledge: a case study on multi-agent robotics fault diagnosis and prediction." Artificial Life and Robotics (2026).

BibTeX: Download