Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering

TL;DR

Aegis is an advanced multi-agent system based on large language models designed to assist with complex functional safety tasks in automotive engineering, utilizing retrieval-augmented generation and expert prompt refinement.

Contribution

The paper introduces Aegis, a novel LLM-based multi-agent tailored for automotive functional safety, incorporating RAG and reflective mechanisms for improved task management.

Findings

Aegis effectively supports hazard analysis and safety documentation.

Aegis-Max enhances performance with retrieval-augmented generation.

Prompt refinement by safety experts improves Aegis accuracy.

Abstract

Functional safety is a critical aspect of automotive engineering, encompassing all phases of a vehicle's lifecycle, including design, development, production, operation, and decommissioning. This domain involves highly knowledge-intensive tasks. This paper introduces Aegis: An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering. Aegis is specifically designed to support complex functional safety tasks within the automotive sector. It is tailored to perform Hazard Analysis and Risk Assessment(HARA), document Functional Safety Requirements(FSR), and plan test cases for Automatic Emergency Braking(AEB) systems. The most advanced version, Aegis-Max, leverages Retrieval-Augmented Generation(RAG) and reflective mechanisms to enhance its capability in managing complex, knowledge-intensive tasks. Additionally, targeted prompt refinement by professional functional safety practitioners can significantly optimize Aegis's performance in the functional safety domain. This paper demonstrates the potential of Aegis to improve the efficiency and effectiveness of functional safety processes in automotive engineering.