Umeå University's logo

umu.sePublications
EnglishSvenskaNorsk
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • 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
Teaming up with agentic swarms in personalized behavior change systems
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0003-1290-9441
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0002-9963-7639
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0002-8430-4241
2026 (English)In: HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction / [ed] Osawa H., Lindgren H., Steinfeld A., Foster M.E., Okada S., Zhu H., Association for Computing Machinery, Inc , 2026, p. 554-556Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

We present a novel architecture for Human-AI Teaming with a swarm of role-based agents supporting healthy behavior change. The system consists of a Triage Agent, RAG agent, and four specialized agents (Empathic Companion, Persuasive Challenging Coach, Medical Domain Expert, and Neutral Assistant) that communicate decentrally. Evaluated with six participants, results showed positive attitudes toward behavior change, with participants finding the system useful and responding favorably to personalized suggestions across physical activity, nutrition, alcohol, and recovery domains.
Place, publisher, year, edition, pages
Association for Computing Machinery, Inc , 2026. p. 554-556
Keywords [en]
Behavior Change, Human-AI Interaction, Human-AI Teaming, Personalization
National Category
Human Computer Interaction
Identifiers
URN: urn:nbn:se:umu:diva-248882DOI: 10.1145/3765766.3765871ISI: 001731727900106Scopus ID: 2-s2.0-105027422785ISBN: 9798400721786 (electronic)OAI: oai:DiVA.org:umu-248882DiVA, id: diva2:2106340
Conference
13th International Conference on Human-Agent Interaction, HAI 2025, Yokohama, Japan, November 10-13, 2025
Available from: 2026-09-29 Created: 2026-09-29 Last updated: 2026-09-29Bibliographically approved

Open Access in DiVA

fulltext(423 kB)20 downloads
File information
File name FULLTEXT01.pdfFile size 423 kBChecksum SHA-512
ce6d66ed69d6dca589896e4d315681975d52f33dfe709cab59971c194ca275dea3fb257b2fedff6766a115f0d5b8171fe4d613713cccb1e54087f69373e987fd
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Kilic, KaanKaelin, Vera C.Yildiz, ErenLindgren, Helena

Search in DiVA

By author/editor
Kilic, KaanKaelin, Vera C.Yildiz, ErenLindgren, Helena
By organisation
Department of Computing Science
Human Computer Interaction

Search outside of DiVA

GoogleGoogle Scholar
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: 409 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • 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
v. 2.49.0
|
WCAG
|
Log in
|
Manuals
|
Contact the Library