Anastasia Kuzminykh | The power of discussion: Designing useful communication with AI agents

Описание: Our weekly SRI Seminar Series welcomes Anastasia Kuzminykh, assistant professor at the University of Toronto’s Faculty of Information and a faculty affiliate at the Schwartz Reisman Institute. With a background spanning computer science, psychology, and ethnographic research, Kuzminykh’s work bridges human-computer interaction and the design of intelligent systems.

Her current research focuses on how people interact with AI systems through conversation—exploring trust, reliability, and user perception in human–agent communication. Through The COoKIE Group, Kuzminykh studies how design decisions shape ethical and effective human–AI collaboration, especially in contexts involving large language models, generative tools, and decision-support systems.

Moderator: Avery Slater, Department of English & Drama

Talk title:
“The power of discussion: Designing useful communication with AI agents”

Abstract:
The rapid development of LLM-based interfaces has made interactions with AI systems easily accessible, dynamically adaptable, and most importantly, comprehensible for a wide audience, leading to the unprecedented current popularity of human-AI collaboration. Shifting to this human-agent communication paradigm, empowered by the intuitive nature of conversational interfaces, quickly opened exciting opportunities for users and has already significantly reshaped their information-seeking practices, decision-making processes, creative activities, etc. However, alongside all the promising advances, we started observing numerous worrisome threats to the quality of such human-AI collaboration, including, for example, users’ overreliance on AI, the “gulf of envisioning” challenge with formulating effective prompts, the models’ tendency for sycophantic behaviours, or the issues of potential amplification of biases and intensification of echo chambers. In this talk, I will cover some of the recent work done with my research group toward addressing these challenges and discuss the role of conversation architecture in supporting efficient human-AI collaboration.

Suggested reading:
Paula Akemi Aoyagui, Kelsey Stemmler, Sharon A. Ferguson, Young-Ho Kim, and Anastasia Kuzminykh, “A matter of perspective (s): Contrasting human and llm argumentation in subjective decision-making on subtle sexism.” In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pp. 1–16. 2025.

Sharon Ferguson, Paula Akemi Aoyagui, Rimsha Rizvi, Young-Ho Kim, and Anastasia Kuzminykh, “The explanation that hits home: The characteristics of verbal explanations that affect human perception in subjective decision-making.” Proceedings of the ACM on Human-Computer Interaction 8, no. CSCW2 (2024): 1–37.

Brennan Jones, Kelsey Stemmler, Emily Su, Young-Ho Kim, and Anastasia Kuzminykh, “Users’ expectations and practices with agent memory.” In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–8. 2025.

About Anastasia Kuzminykh
Anastasia Kuzminykh is an assistant professor at the University of Toronto in the Faculty of Information, cross-appointed to the Department of Computer Science. She is an associate director of the Knowledge Media Design Institute, a faculty member of the Data Science Institute, a faculty affiliate with the Schwartz Reisman Institute for Technology and Society, and the director of the Toronto Human-AI Interaction Research School (THAI RS).

Kuzminykh leads the COoKIE AI research group (communication, organization of knowledge, information ecosystems), which focuses on designing interactive intelligent systems, such as AI agents, GenAI tools, and AI-based decision support systems, that are effective, efficient, and ethical. Her research advances and shapes human-AI collaboration, exploring human perceptions of AI systems and the information they produce, their implications for human-AI communication design, and AI ethicality and complementarity. In addition to a PhD in computer science from the University of Waterloo, her research path includes experiences in anthropology, cognitive and neuropsychology, systems design engineering, and information science, which allows her to combine diverse theoretical and practical approaches in her research program. Dr. Kuzminykh actively collaborates with industry and academia worldwide; her work is internationally recognized through awards and extensive funding, continuously published in the leading international venues in human-computer interaction and AI, and gets broad coverage on TV, radio, and online media.

About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.