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 (2025)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2025

Publisher: International Symposium on Swarm Behavior and Bio-Inspired Robotics (SWARM)

City/Town: Göttingen, Germany

Pages Range: 8

Conference Proceedings Title: Tagungsband International Symposium on Swarm Behavior and Bio-Inspired Robotics

Event location: Göttingen DE

URI: https://www25.swarm-systems.org/

Abstract

The rapid advancement of large language models (LLMs) has revealed their impressive capabilities in semantic understanding and logical reasoning over text-based data. These developments open new avenues for integrating LLMbased inference with high-value domain knowledge from human experts. However, expert knowledge is often unstructured and limited in volume, particularly within specific industrial domains, rendering traditional fine-tuning approaches impractical. In this work, we propose a novel and efficient framework that facilitates integrating expert knowledge from a Delphi study into LLMs. We validate our framework through a case study on a predictive maintenance (PdM) use case involving mobile robotic systems, demonstrating notable inference performance improvements with human experts’ knowledge and the feasibility of leveraging expert knowledge in data-scarce environments. I

Authors with CRIS profile

Yongxu Ren Lehrstuhl für Autonome Systeme und Mechatronik Felix Deichsel Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Jürgen Seiler Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Andre Kaup Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Philipp Beckerle Lehrstuhl für Autonome Systeme und Mechatronik

How to cite

APA:

Ren, Y., Deichsel, F., Seiler, J., Kaup, A., & Beckerle, P. (2025). Enhancing LLM Inference with Human Expert Knowledge: A Case Study on Multi-Agent Robotics Fault Diagnosis and Prediction. In Tagungsband International Symposium on Swarm Behavior and Bio-Inspired Robotics (pp. 8). Göttingen, DE: Göttingen, Germany: International Symposium on Swarm Behavior and Bio-Inspired Robotics (SWARM).

MLA:

Ren, Yongxu, et al. "Enhancing LLM Inference with Human Expert Knowledge: A Case Study on Multi-Agent Robotics Fault Diagnosis and Prediction." Proceedings of the International Symposium on Swarm Behavior and Bio-Inspired Robotics, Göttingen Göttingen, Germany: International Symposium on Swarm Behavior and Bio-Inspired Robotics (SWARM), 2025. 8.

BibTeX: Download