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

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-Base...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-10
Hauptverfasser: Lu, Shi, Qi, Bin, Luo, Jiarui, Zhang, Yang, Liang, Zhanzhao, Gao, Zhaowei, Deng, Wenke, Sun, Lin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Lu, Shi
Qi, Bin
Luo, Jiarui
Zhang, Yang
Liang, Zhanzhao
Gao, Zhaowei
Deng, Wenke
Sun, Lin
description 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.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3118116542</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3118116542</sourcerecordid><originalsourceid>FETCH-proquest_journals_31181165423</originalsourceid><addsrcrecordid>eNqNi9EKgjAYRkcQJOU7DLoW3KYm3a1QCuyqupahvzIZ_8rNoLdPogfo6jsHzrcgAReCRXnC-YqEzg1xHPNsx9NUBOQuodduL5HK9qWwgZZW1SU6KDfTZTJeR7IH9LSzIz2jB2P018sJG68tKkOvqgP_pgX2GgFGjf2GLDtlHIS_XZNtWdyOp-gx2ucEzteDncb562rBWM5YliZc_Fd9ABfwP8o</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3118116542</pqid></control><display><type>article</type><title>Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering</title><source>Free E- Journals</source><creator>Lu, Shi ; Qi, Bin ; Luo, Jiarui ; Zhang, Yang ; Liang, Zhanzhao ; Gao, Zhaowei ; Deng, Wenke ; Sun, Lin</creator><creatorcontrib>Lu, Shi ; Qi, Bin ; Luo, Jiarui ; Zhang, Yang ; Liang, Zhanzhao ; Gao, Zhaowei ; Deng, Wenke ; Sun, Lin</creatorcontrib><description>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.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Hazard assessment ; Knowledge management ; Multiagent systems ; Task complexity</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Lu, Shi</creatorcontrib><creatorcontrib>Qi, Bin</creatorcontrib><creatorcontrib>Luo, Jiarui</creatorcontrib><creatorcontrib>Zhang, Yang</creatorcontrib><creatorcontrib>Liang, Zhanzhao</creatorcontrib><creatorcontrib>Gao, Zhaowei</creatorcontrib><creatorcontrib>Deng, Wenke</creatorcontrib><creatorcontrib>Sun, Lin</creatorcontrib><title>Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering</title><title>arXiv.org</title><description>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.</description><subject>Hazard assessment</subject><subject>Knowledge management</subject><subject>Multiagent systems</subject><subject>Task complexity</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi9EKgjAYRkcQJOU7DLoW3KYm3a1QCuyqupahvzIZ_8rNoLdPogfo6jsHzrcgAReCRXnC-YqEzg1xHPNsx9NUBOQuodduL5HK9qWwgZZW1SU6KDfTZTJeR7IH9LSzIz2jB2P018sJG68tKkOvqgP_pgX2GgFGjf2GLDtlHIS_XZNtWdyOp-gx2ucEzteDncb562rBWM5YliZc_Fd9ABfwP8o</recordid><startdate>20241017</startdate><enddate>20241017</enddate><creator>Lu, Shi</creator><creator>Qi, Bin</creator><creator>Luo, Jiarui</creator><creator>Zhang, Yang</creator><creator>Liang, Zhanzhao</creator><creator>Gao, Zhaowei</creator><creator>Deng, Wenke</creator><creator>Sun, Lin</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241017</creationdate><title>Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering</title><author>Lu, Shi ; Qi, Bin ; Luo, Jiarui ; Zhang, Yang ; Liang, Zhanzhao ; Gao, Zhaowei ; Deng, Wenke ; Sun, Lin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31181165423</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Hazard assessment</topic><topic>Knowledge management</topic><topic>Multiagent systems</topic><topic>Task complexity</topic><toplevel>online_resources</toplevel><creatorcontrib>Lu, Shi</creatorcontrib><creatorcontrib>Qi, Bin</creatorcontrib><creatorcontrib>Luo, Jiarui</creatorcontrib><creatorcontrib>Zhang, Yang</creatorcontrib><creatorcontrib>Liang, Zhanzhao</creatorcontrib><creatorcontrib>Gao, Zhaowei</creatorcontrib><creatorcontrib>Deng, Wenke</creatorcontrib><creatorcontrib>Sun, Lin</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lu, Shi</au><au>Qi, Bin</au><au>Luo, Jiarui</au><au>Zhang, Yang</au><au>Liang, Zhanzhao</au><au>Gao, Zhaowei</au><au>Deng, Wenke</au><au>Sun, Lin</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering</atitle><jtitle>arXiv.org</jtitle><date>2024-10-17</date><risdate>2024</risdate><eissn>2331-8422</eissn><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.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_3118116542
source Free E- Journals
subjects Hazard assessment
Knowledge management
Multiagent systems
Task complexity
title Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T01%3A03%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Aegis:An%20Advanced%20LLM-Based%20Multi-Agent%20for%20Intelligent%20Functional%20Safety%20Engineering&rft.jtitle=arXiv.org&rft.au=Lu,%20Shi&rft.date=2024-10-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3118116542%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3118116542&rft_id=info:pmid/&rfr_iscdi=true