BEHAVE AI: BEst Practices and Guidelines for Human-Centric Design and EvAluation of ProactiVE AI Agents
Kraus, Matthias; Zepf, Sebastian; Westhäußer, Rebecca; Feustel, Isabel; Zargham, Nima; Aslan, Ilhan; Edwards, Justin; Mayer, Sven; Kontogiorgos, Dimosthenis; Wagner, Nicolas; André, Elisabeth (2025-03-24)
ACM
24.03.2025
Matthias Kraus, Sebastian Zepf, Rebecca Westhäußer, Isabel Feustel, Nima Zargham, Ilhan Aslan, Justin Edwards, Sven Mayer, Dimosthenis Kontogiorgos, Nicolas Wagner, and Elisabeth André. 2025. BEHAVE AI: BEst Practices and Guidelines for Human-Centric Design and EvAluation of ProactiVE AI Agents. In Companion Proceedings of the 30th International Conference on Intelligent User Interfaces (IUI '25 Companion). Association for Computing Machinery, New York, NY, USA, 175–178. https://doi.org/10.1145/3708557.3716155
https://rightsstatements.org/vocab/InC/1.0/
© Owner/Author 2025. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in IUI'25 : Companion Proceedings of the 2025 Conference on Intelligent User Interfaces, http://dx.doi.org/10.1145/10.1145/3708557.3716155.
https://rightsstatements.org/vocab/InC/1.0/
© Owner/Author 2025. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in IUI'25 : Companion Proceedings of the 2025 Conference on Intelligent User Interfaces, http://dx.doi.org/10.1145/10.1145/3708557.3716155.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202505123249
https://urn.fi/URN:NBN:fi:oulu-202505123249
Tiivistelmä
Abstract
The last years have seen a significant rise in interest in highly autonomous and proactive agents fueled by the progress of AI. While there is various research on the design, implementation, and evaluation of proactive agents, there remains a critical gap in the methodologies used for both design and evaluation, which are largely informed by reactive system design principles. Our full-day multidisciplinary workshop brings together researchers and practitioners from the IUI community in academia and industry to understand the challenges of designing and evaluating proactive agents in a human-centric manner. We will reflect on existing evaluation methods, identify challenges in designing proactive systems, and discuss potential solutions, best practices, and human-centric guidelines to bridge these gaps. Ultimately, our goal is to map out key focus areas and research challenges, fostering strong interdisciplinary relationships within and across fields related to Artificial Intelligence (AI) and Human-Computer Interaction (HCI).
The last years have seen a significant rise in interest in highly autonomous and proactive agents fueled by the progress of AI. While there is various research on the design, implementation, and evaluation of proactive agents, there remains a critical gap in the methodologies used for both design and evaluation, which are largely informed by reactive system design principles. Our full-day multidisciplinary workshop brings together researchers and practitioners from the IUI community in academia and industry to understand the challenges of designing and evaluating proactive agents in a human-centric manner. We will reflect on existing evaluation methods, identify challenges in designing proactive systems, and discuss potential solutions, best practices, and human-centric guidelines to bridge these gaps. Ultimately, our goal is to map out key focus areas and research challenges, fostering strong interdisciplinary relationships within and across fields related to Artificial Intelligence (AI) and Human-Computer Interaction (HCI).
Kokoelmat
- Avoin saatavuus [38618]