Malmö University Publications
Planned maintenance
A system upgrade is planned for 17/11-2026, at 12:00-13:00. During this time DiVA will be unavailable.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework
Siemens AG, Eindhoven University of Technology München, Germany.ORCID iD: 0009-0009-3748-3273
Siemens AG München, Germany.ORCID iD: 0009-0007-0440-030X
Siemens AG München, Germany.ORCID iD: 0009-0008-0007-4575
Siemens AG München, Germany.ORCID iD: 0009-0003-2503-4741
Show others and affiliations
2026 (English)In: Proceedings - 2026 IEEE/ACM 5th International Conference on AI Engineering - Software Engineering for AI, CAIN 2026, Association for Computing Machinery, Inc , 2026, p. 271-281Conference paper, Published paper (Refereed)
Abstract [en]

Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting expert time. This paper investigates how to capture and embed human domain knowledge into AI agent systems through an industrial case study. We propose a software engineering framework to capture human domain knowledge for engineering AI agents in simulation data visualization by augmenting a Large Language Model (LLM) with a request classifier, Retrieval-Augmented Generation (RAG) system for code generation, codified expert rules, and visualization design principles unified in an agent demonstrating autonomous, reactive, proactive, and social behavior. Evaluation across five scenarios spanning multiple engineering domains with 12 evaluators demonstrates 206% improvement in output quality, with our agent achieving expert-level ratings in all cases versus baseline's poor performance, while maintaining superior code quality with lower variance. Our contributions are: an automated agent-based system for visualization generation and a validated framework for systematically capturing human domain knowledge and codifying tacit expert knowledge into AI agents, demonstrating that non-experts can achieve expert-level outcomes in specialized domains.

Place, publisher, year, edition, pages
Association for Computing Machinery, Inc , 2026. p. 271-281
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mau:diva-88612DOI: 10.1145/3793653.3793776Scopus ID: 2-s2.0-105052397240ISBN: 9798400724756 (electronic)OAI: oai:DiVA.org:mau-88612DiVA, id: diva2:2109652
Conference
5th IEEE International Conference on AI Engineering - Software Engineering for AI, CAIN 2026, 12-13 Apr 2026, Rio de Janeiro, Brazil
Available from: 2026-10-12 Created: 2026-10-12 Last updated: 2026-10-12Bibliographically approved

Open Access in DiVA

fulltext(2965 kB)34 downloads
File information
File name FULLTEXT01.pdfFile size 2965 kBChecksum SHA-512
7de67672e65bf07dd8e17ca7bc6d1a681d031262fdf2b4e7e2ec4dd3ee0dbe24d226588792652306c688885c1a20b88da496380b884dae6e455db747eff5e4f1
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Olsson, Helena Holmström

Search in DiVA

By author/editor
Uulu, Choro UlanKulyabin, MikhailFuhrmann, IrisJoosten, JanPacheco, Nuno Miguel MartinsPetridis, FilipposJohnson, RebeccaBosch, JanOlsson, Helena Holmström
By organisation
Department of Computer Science and Media Technology (DVMT)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 34 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 9662 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf