Proactive Systems in HCI and AI: Concepts, Challenges, and Opportunities

Anastasia Kuzminykh; Cosmin Munteanu; Jaisie Sin; Nima Zargham; Sharon Ferguson

arxiv: 2606.25149 · v1 · pith:DSM67TG6new · submitted 2026-06-23 · 💻 cs.HC · cs.AI

Proactive Systems in HCI and AI: Concepts, Challenges, and Opportunities

Nima Zargham , Sharon Ferguson , Jaisie Sin , Cosmin Munteanu , Anastasia Kuzminykh This is my paper

Pith reviewed 2026-06-25 21:55 UTC · model grok-4.3

classification 💻 cs.HC cs.AI

keywords proactive systemshuman-computer interactionartificial intelligencesystem designevaluation methodsuser controltransparencytrust

0 comments

The pith

The term proactivity is applied inconsistently across systems, conflating distinct behaviors and blocking systematic design and evaluation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that proactivity lacks a shared definition, so reminders and autonomous planning agents often receive the same label despite different mechanisms. This ambiguity stops researchers from comparing systems or building on one another's work. Design and evaluation methods still assume reactive interactions and therefore miss issues specific to proactive ones, such as deciding when to act or preserving user control. The workshop is organized to create a common conceptualization, map the resulting gaps, and produce human-centered guidelines for future systems.

Core claim

Despite growing interest in systems that anticipate needs and act without explicit input, the concept of proactivity remains loosely defined and inconsistently applied. Simple notifications and complex planning agents are frequently grouped together even though their underlying mechanisms and intentions differ. This conflation limits the ability to design, compare, and evaluate such systems in a rigorous way. Existing methodologies, rooted in reactive paradigms, do not address the distinct challenges of timing, appropriateness, user control, transparency, and trust.

What carries the argument

The inconsistently applied concept of proactivity that groups fundamentally different system behaviors under one label.

If this is right

A shared conceptualization would enable direct comparison of proactive systems across applications.
Guidelines that incorporate timing and user control would change how new systems are built.
Identification of gaps in current methods would point to specific research needs in HCI and AI.
Co-created evaluation frameworks would support more reliable assessment of transparency and trust.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Resolving the definitional issue could change how acceptance studies measure proactive features in deployed products.
The same ambiguity may appear in regulatory discussions of autonomous assistants and their required safeguards.
Clearer distinctions could help separate proactivity research from adjacent topics such as recommender systems or notification design.

Load-bearing premise

That the varied uses of the term proactivity actually mix behaviors with distinct mechanisms and intentions.

What would settle it

A literature review or survey of researchers that finds consistent, non-overlapping definitions of proactivity across published work.

read the original abstract

The last few years have seen a significant rise in interest in highly autonomous and proactive systems, fueled by advances in AI. Systems that anticipate user needs, take initiative, and act without explicit user input. Such systems span a wide range of applications, from smart lighting that adapts to user activity to assistive robots that plan actions in advance to intelligent thermostats that learn routines and adjust environments proactively. Despite this breadth, the concept of proactivity remains loosely defined and inconsistently applied across research and practice. Current usage of the term often conflates fundamentally different system behaviors. For instance, simple reminders or recommendation systems are frequently labeled as proactive, even though underlying mechanisms and intentions differ significantly. This conceptual ambiguity limits our ability to systematically design, compare, and evaluate proactive systems. Moreover, existing methodologies for design and evaluation are largely rooted in reactive interaction paradigms, failing to address the unique challenges posed by proactive behavior, including timing, appropriateness, user control, transparency, and trust. This multidisciplinary workshop aims to establish a clearer and more rigorous foundation for understanding proactive systems. We bring together researchers and practitioners from Human-Computer Interaction, AI, and related fields to (1) develop a shared conceptualization of proactivity, (2) identify gaps and limitations in current design and evaluation approaches, and (3) co-create human-centered guidelines and research directions for future systems. Through interactive discussions and collaborative activities, the workshop seeks to map key challenges and opportunities, ultimately advancing robust and consistent frameworks for designing and evaluating proactive technologies.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a workshop proposal that flags loose use of 'proactivity' in HCI and AI but supplies no new definitions, examples, or data to back the claim.

read the letter

This is a workshop proposal that correctly identifies loose and inconsistent use of the term "proactivity" in HCI and AI research, but it stops short of offering any new definitions, examples with citations, or data to show how widespread the problem is. The authors note that reminders and recommendations get called proactive even when they differ from systems that anticipate needs without input, and they argue that evaluation methods stay stuck in reactive models. That observation lines up with what I've seen in the area.

What the paper does well is bring together HCI, AI, and related fields to push for shared conceptualization, gap identification, and guidelines on timing, control, transparency, and trust. The abstract lays out three clear goals for the workshop and mentions applications like smart lighting, assistive robots, and thermostats. This kind of agenda-setting can help organize scattered work if the event draws the right people.

The soft spots are mostly around the lack of grounding. The claim of conceptual ambiguity is stated but not illustrated with specific papers or cases, which makes it harder to gauge the scope. Existing methodologies are called out as reactive without naming which ones or how they fall short in practice. Since this is positioned as a position statement rather than a research report, those gaps are understandable, but they do limit how much a reader can take away beyond the call to action.

This kind of document is for researchers and practitioners already interested in proactive or autonomous systems who might attend or contribute to the workshop. Someone looking for a technical advance or a tested framework won't get much here. It could still be useful for sparking discussion.

I would bring this to a reading group if the group is focused on conceptual issues in HCI, but probably as a maybe rather than a must-read. It doesn't have results to cite in my own work. The topic is relevant enough that it deserves peer review as a workshop proposal, even if the output will depend on what happens at the event.

Referee Report

2 major / 0 minor

Summary. The manuscript proposes a multidisciplinary workshop on proactive systems in HCI and AI. It claims that the concept of proactivity is loosely defined and inconsistently applied across research and practice, with usage often conflating fundamentally different behaviors (e.g., simple reminders or recommendations versus systems that anticipate needs and act without explicit input). This ambiguity is said to limit systematic design, comparison, and evaluation. Existing methodologies are described as rooted in reactive paradigms and inadequate for addressing challenges unique to proactivity such as timing, appropriateness, user control, transparency, and trust. The workshop seeks to develop a shared conceptualization, identify gaps, and co-create human-centered guidelines through discussions and collaborative activities.

Significance. As an agenda-setting document, the proposal identifies a timely issue in an area driven by recent AI advances, with potential to improve consistency in an emerging subfield spanning smart environments, assistive robots, and adaptive interfaces. Successful execution could yield shared frameworks that enable better cross-study comparison and human-centered design practices. The manuscript itself advances no new empirical findings, formal definitions, or testable hypotheses, functioning instead as a call for community input.

major comments (2)

[Abstract] Abstract: The central claim that 'the concept of proactivity remains loosely defined and inconsistently applied across research and practice' and that 'current usage of the term often conflates fundamentally different system behaviors' is advanced without citations to prior work or a systematic mapping of usage patterns in the literature. This leaves the scope and impact of the described ambiguity undemonstrated.
[Abstract] Abstract: The assertion that 'existing methodologies for design and evaluation are largely rooted in reactive interaction paradigms' is presented without reference to specific methodologies, frameworks, or studies, making it difficult to evaluate the claimed gap or the unique challenges listed (timing, appropriateness, etc.).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on our workshop proposal. We agree that the abstract would be strengthened by additional citations and will revise accordingly while preserving the document's focus as an agenda-setting call for community input rather than a systematic review.

read point-by-point responses

Referee: [Abstract] Abstract: The central claim that 'the concept of proactivity remains loosely defined and inconsistently applied across research and practice' and that 'current usage of the term often conflates fundamentally different system behaviors' is advanced without citations to prior work or a systematic mapping of usage patterns in the literature. This leaves the scope and impact of the described ambiguity undemonstrated.

Authors: We acknowledge the value of supporting citations. Although the proposal is not intended as a literature review, we will add references to prior work in HCI and AI that has identified inconsistencies in the use of 'proactivity' (e.g., studies on proactive assistants and adaptive interfaces). This will illustrate the scope of the issue without shifting the manuscript's purpose toward a systematic mapping, which remains a goal for the workshop itself. revision: yes
Referee: [Abstract] Abstract: The assertion that 'existing methodologies for design and evaluation are largely rooted in reactive interaction paradigms' is presented without reference to specific methodologies, frameworks, or studies, making it difficult to evaluate the claimed gap or the unique challenges listed (timing, appropriateness, etc.).

Authors: We agree that explicit references would improve clarity. In revision we will cite established HCI approaches such as traditional usability testing and user-centered design frameworks that emphasize reactive, user-initiated interactions, and note how they fall short for proactive challenges. This addition will contextualize the listed issues without expanding the proposal into a methods critique. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The document is a workshop proposal and position statement containing no equations, derivations, fitted parameters, predictions, or formal definitions. Central statements are motivational descriptions of perceived field issues and a call for discussion; no load-bearing steps exist that reduce by construction to inputs, self-citations, or ansatzes. The text is self-contained as an agenda-setting document with no testable claims or derivation chains to inspect.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a conceptual workshop proposal with no mathematical models, empirical measurements, or technical derivations, so the ledger contains no entries.

pith-pipeline@v0.9.1-grok · 5813 in / 956 out tokens · 28686 ms · 2026-06-25T21:55:42.897767+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

36 extracted references · 18 canonical work pages

[1]

Alafate Abulimiti, Paola R. Peña, Fatemeh Alizadeh, Shashank Ahire, Heloisa Candello, Smit Desai, Justin Edwards, Yuan He, Darragh Higgins, Alberto Jovane, Matthias Kraus, Guy Laban, Rachel McDonnell, Jairo Pérez-Osorio, Tanja Schnee- berger, Jaisie Sin, Tobias Thejll-Madsen, Nima Zargham, and Benjamin R. Cowan
[2]

InAdjunct Proceedings of the 25th ACM International Confer- ence on Intelligent Virtual Agents (IV A Adjunct ’25)

DEBP-PVA: Designing and Evaluating Behavioral Paradigms With Proac- tive Virtual Agents. InAdjunct Proceedings of the 25th ACM International Confer- ence on Intelligent Virtual Agents (IV A Adjunct ’25). Association for Computing Machinery, New York, NY, USA, Article 3, 4 pages. doi:10.1145/3742886.3758118

work page doi:10.1145/3742886.3758118
[3]

Guidelines for Human-AI Interaction,

Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. 2019. Guidelines for Human- AI Interaction. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(Glasgow, Scotland Uk)(CHI ’19). Associa...

work page doi:10.1145/3290605.3300233 2019
[4]

Friehs, Dimosthenis Kontogiorgos, Nina Wenig, and Rainer Malaka

Vino Avanesi, Johanna Rockstroh, Thomas Mildner, Nima Zargham, Leon Re- icherts, Maximilian A. Friehs, Dimosthenis Kontogiorgos, Nina Wenig, and Rainer Malaka. 2023. From C-3PO to HAL: Opening The Discourse About The Dark Side of Multi-Modal Social Agents. InProceedings of ACM CUI(Eindhoven, Nether- lands). ACM, New York, NY, USA, Article 62, 7 pages

2023
[5]

Caterina Bérubé, Marcia Nißen, Rasita Vinay, Alexa Geiger, Tobias Budig, Aashish Bhandari, Catherine Rachel Pe Benito, Nathan Ibarcena, Olivia Pistolese, Pan Li, et al. 2024. Proactive behavior in voice assistants: A systematic review and conceptual model.Computers in Human Behavior Reports(2024), 100411

2024
[6]

John Brooke. 2013. SUS: a retrospective.Journal of usability studies8, 2 (2013), 29–40

2013
[7]

Sera Buyukgoz, Amit Kumar Pandey, Marine Chamoux, and Mohamed Chetouani
[8]

doi:10.3389/frobt.2021.694177

Exploring Behavioral Creativity of a Proactive Robot.Frontiers in Robotics and AIVolume 8 - 2021 (2021). doi:10.3389/frobt.2021.694177

work page doi:10.3389/frobt.2021.694177 2021
[9]

J Michael Crant. 2000. Proactive behavior in organizations.Journal of manage- ment26, 3 (2000), 435–462

2000
[10]

Smit Desai, Mateusz Dubiel, Nima Zargham, Thomas Mildner, and Laura Spillner
[11]

InProceedings of the 7th ACM Conference on Conversational User Interfaces (CUI ’25)

Personas Evolved: Designing Ethical LLM-Based Conversational Agent Personalities. InProceedings of the 7th ACM Conference on Conversational User Interfaces (CUI ’25). Association for Computing Machinery, New York, NY, USA, Article 32, 4 pages. doi:10.1145/3719160.3728624

work page doi:10.1145/3719160.3728624
[12]

Smit Desai, Christina Ziying Wei, Jaisie Sin, Mateusz Dubiel, Nima Zargham, Shashank Ahire, Martin Porcheron, Anastasia Kuzminykh, Minha Lee, Heloisa Candello, Joel E Fischer, Cosmin Munteanu, and Benjamin R. Cowan. 2024. CUI@CHI 2024: Building Trust in CUIs—From Design to Deployment. InExtened abstracts of ACM CHI(Honolulu, HI, USA). ACM, New York, NY, U...

2024
[13]

Mateusz Dubiel, Smit Desai, Nima Zargham, and Anuschka Schmitt. 2024. Voice- craft: Designing Task-specific Voice Assistant Personas. InProceedings of the 6th GI ’26, June 9–12, 2026, Waterloo, ON, Canada Zargham et al. ACM Conference on Conversational User Interfaces(Luxembourg, Luxembourg) (CUI ’24). Association for Computing Machinery, New York, NY, US...

work page doi:10.1145/3640794.3670000 2024
[14]

Michael Frese and Doris Fay. 2001. 4. Personal initiative: An active performance concept for work in the 21st century.Research in organizational behavior23 (2001), 133–187

2001
[15]

Alyssa Glass, Deborah L McGuinness, and Michael Wolverton. 2008. Toward establishing trust in adaptive agents. InProceedings of the 13th international conference on Intelligent user interfaces. 227–236

2008
[16]

Eric Horvitz. 1999. Principles of mixed-initiative user interfaces. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(Pittsburgh, Pennsylvania, USA)(CHI ’99). Association for Computing Machinery, New York, NY, USA, 159–166. doi:10.1145/302979.303030

work page doi:10.1145/302979.303030 1999
[17]

Auk Kim, Woohyeok Choi, Jungmi Park, Kyeyoon Kim, and Uichin Lee. 2018. Interrupting Drivers for Interactions: Predicting Opportune Moments for In- vehicle Proactive Auditory-verbal Tasks.Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.2, 4, Article 175 (Dec. 2018), 28 pages. doi:10.1145/3287053

work page doi:10.1145/3287053 2018
[18]

Minyeong Kim, Jiwook Lee, Youngji Koh, Chanhee Lee, Uichin Lee, and Auk Kim. 2024. Interrupting for Microlearning: Understanding Perceptions and Inter- ruptibility of Proactive Conversational Microlearning Services. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machine...

work page doi:10.1145/3613904.3642778 2024
[19]

Matthias Kraus, Diana Betancourt, and Wolfgang Minker. 2023. Does It Affect You? Social and Learning Implications of Using Cognitive-Affective State Recog- nition for Proactive Human-Robot Tutoring. In2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). 928–935. doi:10.1109/RO-MAN57019.2023.10309574

work page doi:10.1109/ro-man57019.2023.10309574 2023
[20]

Matthias Kraus, Nicolas Wagner, Ron Riekenbrauck, and Wolfgang Minker. 2023. Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learn- ing. InProceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization(Limassol, Cyprus)(UMAP ’23). Association for Computing Machinery, New York, NY, USA, 146–155. doi:10.1145/356...

work page doi:10.1145/3565472.3595611 2023
[21]

Matthias Kraus, Sebastian Zepf, Rebecca Westhäußer, Isabel Feustel, Nima Zargham, Ilhan Aslan, Justin Edwards, Sven Mayer, Dimosthenis Kontogior- gos, 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 IUI(Cagliari, Italy). ACM, New...

2025
[22]

Jieun Lim, Youngji Koh, Auk Kim, and Uichin Lee. 2024. Exploring Context- Aware Mental Health Self-Tracking Using Multimodal Smart Speakers in Home Environments. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Article 699, 18 pages. doi:10.1...

work page doi:10.1145/3613904 2024
[23]

Maria Madsen and Shirley Gregor. 2000. Measuring human-computer trust. In 11th australasian conference on information systems, Vol. 53. Citeseer, 6–8

2000
[24]

Cowan, Joel E

Donald McMillan, Razan Jaber, Benjamin R. Cowan, Joel E. Fischer, Bahar Irfan, Ronald Cumbal, Nima Zargham, and Minha Lee. 2023. Human-Robot Conversa- tional Interaction (HRCI). InCompanion of ACM/IEEE HRI(Stockholm, Sweden) (HRI ’23). ACM, New York, NY, USA, 923–925

2023
[25]

Mihale-Wilson, Adrian Hawlitschek, Florian Giger, Florian Müller, Oliver Hinz, and Max Mühlhäuser

Christian Meurisch, Cristina A. Mihale-Wilson, Adrian Hawlitschek, Florian Giger, Florian Müller, Oliver Hinz, and Max Mühlhäuser. 2020. Exploring User Expectations of Proactive AI Systems.Proc. ACM Interact. Mob. Wearable Ubiqui- tous Technol.4, 4, Article 146 (dec 2020), 22 pages. doi:10.1145/3432193

work page doi:10.1145/3432193 2020
[26]

Carl Oechsner, Sven Mayer, and Andreas Butz. 2022. Challenges and Oppor- tunities of Cooperative Robots as Cooking Appliances. InProceedings of the 2022 Workshop on Engaging with Automation(2022-04-30)(AutomationXP’22). https://ceur-ws.org/Vol-3154/paper14.pdf

2022
[28]

Zhenhui Peng, Yunhwan Kwon, Jiaan Lu, Ziming Wu, and Xiaojuan Ma. 2019. Design and Evaluation of Service Robot’s Proactivity in Decision-Making Support Process. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(Glasgow, Scotland Uk)(CHI ’19). Association for Computing Machinery, New York, NY, USA, 1–13. doi:10.1145/3290605.3300328

work page doi:10.1145/3290605.3300328 2019
[29]

Xipei Ren, Gabriele Spina, Simon De Vries, Annick Bijkerk, Babs Faber, and Anna Geraedts. 2020. Understanding Physician’s Experience With Conversational Interfaces During Occupational Health Consultation.IEEE Access8 (2020), 119158– 119169. doi:10.1109/ACCESS.2020.3005733

work page doi:10.1109/access.2020.3005733 2020
[30]

Cowan, Minha Lee, Donald McMillan, and Matthew Peter Aylett

Rachel Ringe, Nima Zargham, Mihai Pomarlan, Benjamin R. Cowan, Minha Lee, Donald McMillan, and Matthew Peter Aylett. 2026. Empowering Human-Robot Communication through Non-linguistic Pathways. InCompanion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction(Edin- burgh, Scotland, UK)(HRI Companion ’26). Association for Comp...

work page doi:10.1145/3776734.3788831 2026
[31]

Martin Schrepp, Andreas Hinderks, and Joörg Thomaschewski. 2017. Construc- tion of a Benchmark for the User Experience Questionnaire (UEQ).International Journal of Interactive Multimedia and Artificial Intelligence4, 4 (2017), 40

2017
[32]

Feger, and Sven Mayer

Maximiliane Windl, Jan Leusmann, Albrecht Schmidt, Sebastian S. Feger, and Sven Mayer. 2024. Privacy Communication Patterns for Domestic Robots. In Tenth Symposium on Usable Privacy and Security (SOUPS 2024)(2024-08-11). USENIX Association, Philadelphia, PA, USA. https://www.usenix.org/conference/ soups2024/presentation/windl

2024
[33]

Neil Yorke-Smith, Shahin Saadati, Karen L Myers, and David N Morley. 2012. The design of a proactive personal agent for task management.International Journal on Artificial Intelligence Tools21, 01 (2012), 1250004

2012
[34]

Nima Zargham, Mateusz Dubiel, Smit Desai, Thomas Mildner, and Hanz-Joachim Belz. 2024. Designing AI Personalities: Enhancing Human-Agent Interaction Through Thoughtful Persona Design. InProceedings of the International Confer- ence on Mobile and Ubiquitous Multimedia (MUM ’24). Association for Computing Machinery, New York, NY, USA, 490–494. doi:10.1145/3...

work page doi:10.1145/3701571.3701608 2024
[35]

Nima Zargham, Leon Reicherts, Vino Avanesi, Yvonne Rogers, and Rainer Malaka
[36]

InProceedings of the 22nd International Conference on Mobile and Ubiquitous Multimedia(Vienna, Austria)(MUM ’23)

Tickling Proactivity: Exploring the Use of Humor in Proactive Voice Assistants. InProceedings of the 22nd International Conference on Mobile and Ubiquitous Multimedia(Vienna, Austria)(MUM ’23). Association for Computing Machinery, New York, NY, USA, 294–320. doi:10.1145/3626705.3627777

work page doi:10.1145/3626705.3627777
[37]

Nima Zargham, Leon Reicherts, Michael Bonfert, Sarah Theres Voelkel, Johannes Schoening, Rainer Malaka, and Yvonne Rogers. 2022. Understanding Circum- stances for Desirable Proactive Behaviour of Voice Assistants: The Proactivity Dilemma. InProceedings of the 4th Conference on Conversational User Interfaces (Glasgow, United Kingdom)(CUI ’22). Association ...

work page doi:10.1145/3543829.3543834 2022

[1] [1]

Alafate Abulimiti, Paola R. Peña, Fatemeh Alizadeh, Shashank Ahire, Heloisa Candello, Smit Desai, Justin Edwards, Yuan He, Darragh Higgins, Alberto Jovane, Matthias Kraus, Guy Laban, Rachel McDonnell, Jairo Pérez-Osorio, Tanja Schnee- berger, Jaisie Sin, Tobias Thejll-Madsen, Nima Zargham, and Benjamin R. Cowan

[2] [2]

InAdjunct Proceedings of the 25th ACM International Confer- ence on Intelligent Virtual Agents (IV A Adjunct ’25)

DEBP-PVA: Designing and Evaluating Behavioral Paradigms With Proac- tive Virtual Agents. InAdjunct Proceedings of the 25th ACM International Confer- ence on Intelligent Virtual Agents (IV A Adjunct ’25). Association for Computing Machinery, New York, NY, USA, Article 3, 4 pages. doi:10.1145/3742886.3758118

work page doi:10.1145/3742886.3758118

[3] [3]

Guidelines for Human-AI Interaction,

Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. 2019. Guidelines for Human- AI Interaction. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(Glasgow, Scotland Uk)(CHI ’19). Associa...

work page doi:10.1145/3290605.3300233 2019

[4] [4]

Friehs, Dimosthenis Kontogiorgos, Nina Wenig, and Rainer Malaka

Vino Avanesi, Johanna Rockstroh, Thomas Mildner, Nima Zargham, Leon Re- icherts, Maximilian A. Friehs, Dimosthenis Kontogiorgos, Nina Wenig, and Rainer Malaka. 2023. From C-3PO to HAL: Opening The Discourse About The Dark Side of Multi-Modal Social Agents. InProceedings of ACM CUI(Eindhoven, Nether- lands). ACM, New York, NY, USA, Article 62, 7 pages

2023

[5] [5]

Caterina Bérubé, Marcia Nißen, Rasita Vinay, Alexa Geiger, Tobias Budig, Aashish Bhandari, Catherine Rachel Pe Benito, Nathan Ibarcena, Olivia Pistolese, Pan Li, et al. 2024. Proactive behavior in voice assistants: A systematic review and conceptual model.Computers in Human Behavior Reports(2024), 100411

2024

[6] [6]

John Brooke. 2013. SUS: a retrospective.Journal of usability studies8, 2 (2013), 29–40

2013

[7] [7]

Sera Buyukgoz, Amit Kumar Pandey, Marine Chamoux, and Mohamed Chetouani

[8] [8]

doi:10.3389/frobt.2021.694177

Exploring Behavioral Creativity of a Proactive Robot.Frontiers in Robotics and AIVolume 8 - 2021 (2021). doi:10.3389/frobt.2021.694177

work page doi:10.3389/frobt.2021.694177 2021

[9] [9]

J Michael Crant. 2000. Proactive behavior in organizations.Journal of manage- ment26, 3 (2000), 435–462

2000

[10] [10]

Smit Desai, Mateusz Dubiel, Nima Zargham, Thomas Mildner, and Laura Spillner

[11] [11]

InProceedings of the 7th ACM Conference on Conversational User Interfaces (CUI ’25)

Personas Evolved: Designing Ethical LLM-Based Conversational Agent Personalities. InProceedings of the 7th ACM Conference on Conversational User Interfaces (CUI ’25). Association for Computing Machinery, New York, NY, USA, Article 32, 4 pages. doi:10.1145/3719160.3728624

work page doi:10.1145/3719160.3728624

[12] [12]

Smit Desai, Christina Ziying Wei, Jaisie Sin, Mateusz Dubiel, Nima Zargham, Shashank Ahire, Martin Porcheron, Anastasia Kuzminykh, Minha Lee, Heloisa Candello, Joel E Fischer, Cosmin Munteanu, and Benjamin R. Cowan. 2024. CUI@CHI 2024: Building Trust in CUIs—From Design to Deployment. InExtened abstracts of ACM CHI(Honolulu, HI, USA). ACM, New York, NY, U...

2024

[13] [13]

Mateusz Dubiel, Smit Desai, Nima Zargham, and Anuschka Schmitt. 2024. Voice- craft: Designing Task-specific Voice Assistant Personas. InProceedings of the 6th GI ’26, June 9–12, 2026, Waterloo, ON, Canada Zargham et al. ACM Conference on Conversational User Interfaces(Luxembourg, Luxembourg) (CUI ’24). Association for Computing Machinery, New York, NY, US...

work page doi:10.1145/3640794.3670000 2024

[14] [14]

Michael Frese and Doris Fay. 2001. 4. Personal initiative: An active performance concept for work in the 21st century.Research in organizational behavior23 (2001), 133–187

2001

[15] [15]

Alyssa Glass, Deborah L McGuinness, and Michael Wolverton. 2008. Toward establishing trust in adaptive agents. InProceedings of the 13th international conference on Intelligent user interfaces. 227–236

2008

[16] [16]

Eric Horvitz. 1999. Principles of mixed-initiative user interfaces. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(Pittsburgh, Pennsylvania, USA)(CHI ’99). Association for Computing Machinery, New York, NY, USA, 159–166. doi:10.1145/302979.303030

work page doi:10.1145/302979.303030 1999

[17] [17]

Auk Kim, Woohyeok Choi, Jungmi Park, Kyeyoon Kim, and Uichin Lee. 2018. Interrupting Drivers for Interactions: Predicting Opportune Moments for In- vehicle Proactive Auditory-verbal Tasks.Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.2, 4, Article 175 (Dec. 2018), 28 pages. doi:10.1145/3287053

work page doi:10.1145/3287053 2018

[18] [18]

Minyeong Kim, Jiwook Lee, Youngji Koh, Chanhee Lee, Uichin Lee, and Auk Kim. 2024. Interrupting for Microlearning: Understanding Perceptions and Inter- ruptibility of Proactive Conversational Microlearning Services. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machine...

work page doi:10.1145/3613904.3642778 2024

[19] [19]

Matthias Kraus, Diana Betancourt, and Wolfgang Minker. 2023. Does It Affect You? Social and Learning Implications of Using Cognitive-Affective State Recog- nition for Proactive Human-Robot Tutoring. In2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). 928–935. doi:10.1109/RO-MAN57019.2023.10309574

work page doi:10.1109/ro-man57019.2023.10309574 2023

[20] [20]

Matthias Kraus, Nicolas Wagner, Ron Riekenbrauck, and Wolfgang Minker. 2023. Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learn- ing. InProceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization(Limassol, Cyprus)(UMAP ’23). Association for Computing Machinery, New York, NY, USA, 146–155. doi:10.1145/356...

work page doi:10.1145/3565472.3595611 2023

[21] [21]

Matthias Kraus, Sebastian Zepf, Rebecca Westhäußer, Isabel Feustel, Nima Zargham, Ilhan Aslan, Justin Edwards, Sven Mayer, Dimosthenis Kontogior- gos, 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 IUI(Cagliari, Italy). ACM, New...

2025

[22] [22]

Jieun Lim, Youngji Koh, Auk Kim, and Uichin Lee. 2024. Exploring Context- Aware Mental Health Self-Tracking Using Multimodal Smart Speakers in Home Environments. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Article 699, 18 pages. doi:10.1...

work page doi:10.1145/3613904 2024

[23] [23]

Maria Madsen and Shirley Gregor. 2000. Measuring human-computer trust. In 11th australasian conference on information systems, Vol. 53. Citeseer, 6–8

2000

[24] [24]

Cowan, Joel E

Donald McMillan, Razan Jaber, Benjamin R. Cowan, Joel E. Fischer, Bahar Irfan, Ronald Cumbal, Nima Zargham, and Minha Lee. 2023. Human-Robot Conversa- tional Interaction (HRCI). InCompanion of ACM/IEEE HRI(Stockholm, Sweden) (HRI ’23). ACM, New York, NY, USA, 923–925

2023

[25] [25]

Mihale-Wilson, Adrian Hawlitschek, Florian Giger, Florian Müller, Oliver Hinz, and Max Mühlhäuser

Christian Meurisch, Cristina A. Mihale-Wilson, Adrian Hawlitschek, Florian Giger, Florian Müller, Oliver Hinz, and Max Mühlhäuser. 2020. Exploring User Expectations of Proactive AI Systems.Proc. ACM Interact. Mob. Wearable Ubiqui- tous Technol.4, 4, Article 146 (dec 2020), 22 pages. doi:10.1145/3432193

work page doi:10.1145/3432193 2020

[26] [26]

Carl Oechsner, Sven Mayer, and Andreas Butz. 2022. Challenges and Oppor- tunities of Cooperative Robots as Cooking Appliances. InProceedings of the 2022 Workshop on Engaging with Automation(2022-04-30)(AutomationXP’22). https://ceur-ws.org/Vol-3154/paper14.pdf

2022

[27] [28]

Zhenhui Peng, Yunhwan Kwon, Jiaan Lu, Ziming Wu, and Xiaojuan Ma. 2019. Design and Evaluation of Service Robot’s Proactivity in Decision-Making Support Process. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(Glasgow, Scotland Uk)(CHI ’19). Association for Computing Machinery, New York, NY, USA, 1–13. doi:10.1145/3290605.3300328

work page doi:10.1145/3290605.3300328 2019

[28] [29]

Xipei Ren, Gabriele Spina, Simon De Vries, Annick Bijkerk, Babs Faber, and Anna Geraedts. 2020. Understanding Physician’s Experience With Conversational Interfaces During Occupational Health Consultation.IEEE Access8 (2020), 119158– 119169. doi:10.1109/ACCESS.2020.3005733

work page doi:10.1109/access.2020.3005733 2020

[29] [30]

Cowan, Minha Lee, Donald McMillan, and Matthew Peter Aylett

Rachel Ringe, Nima Zargham, Mihai Pomarlan, Benjamin R. Cowan, Minha Lee, Donald McMillan, and Matthew Peter Aylett. 2026. Empowering Human-Robot Communication through Non-linguistic Pathways. InCompanion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction(Edin- burgh, Scotland, UK)(HRI Companion ’26). Association for Comp...

work page doi:10.1145/3776734.3788831 2026

[30] [31]

Martin Schrepp, Andreas Hinderks, and Joörg Thomaschewski. 2017. Construc- tion of a Benchmark for the User Experience Questionnaire (UEQ).International Journal of Interactive Multimedia and Artificial Intelligence4, 4 (2017), 40

2017

[31] [32]

Feger, and Sven Mayer

Maximiliane Windl, Jan Leusmann, Albrecht Schmidt, Sebastian S. Feger, and Sven Mayer. 2024. Privacy Communication Patterns for Domestic Robots. In Tenth Symposium on Usable Privacy and Security (SOUPS 2024)(2024-08-11). USENIX Association, Philadelphia, PA, USA. https://www.usenix.org/conference/ soups2024/presentation/windl

2024

[32] [33]

Neil Yorke-Smith, Shahin Saadati, Karen L Myers, and David N Morley. 2012. The design of a proactive personal agent for task management.International Journal on Artificial Intelligence Tools21, 01 (2012), 1250004

2012

[33] [34]

Nima Zargham, Mateusz Dubiel, Smit Desai, Thomas Mildner, and Hanz-Joachim Belz. 2024. Designing AI Personalities: Enhancing Human-Agent Interaction Through Thoughtful Persona Design. InProceedings of the International Confer- ence on Mobile and Ubiquitous Multimedia (MUM ’24). Association for Computing Machinery, New York, NY, USA, 490–494. doi:10.1145/3...

work page doi:10.1145/3701571.3701608 2024

[34] [35]

Nima Zargham, Leon Reicherts, Vino Avanesi, Yvonne Rogers, and Rainer Malaka

[35] [36]

InProceedings of the 22nd International Conference on Mobile and Ubiquitous Multimedia(Vienna, Austria)(MUM ’23)

Tickling Proactivity: Exploring the Use of Humor in Proactive Voice Assistants. InProceedings of the 22nd International Conference on Mobile and Ubiquitous Multimedia(Vienna, Austria)(MUM ’23). Association for Computing Machinery, New York, NY, USA, 294–320. doi:10.1145/3626705.3627777

work page doi:10.1145/3626705.3627777

[36] [37]

Nima Zargham, Leon Reicherts, Michael Bonfert, Sarah Theres Voelkel, Johannes Schoening, Rainer Malaka, and Yvonne Rogers. 2022. Understanding Circum- stances for Desirable Proactive Behaviour of Voice Assistants: The Proactivity Dilemma. InProceedings of the 4th Conference on Conversational User Interfaces (Glasgow, United Kingdom)(CUI ’22). Association ...

work page doi:10.1145/3543829.3543834 2022