cs.HCNov 16, 2026

Human-AI Co-Ideation Across Socio-Technical Configurations: An Interactional Analysis of Planar and Immersive Workspaces

Authors: Orit Shaer, Mary Calabro, Zoe Mitchell, Angelora Cooper, Raffaella Sadun, Andrew L. Kun, Osnat Mokryn

Organizations: Computer Science, Wellesley College, 106 Central st., Wellesley, 02481, MA, USA · Business School, Harvard, Boston, MA, USA · Electrical and Computer Engineering, University of New Hampshire, Durham, NH, USA · Information Systems, University of Haifa, Haifa, Israel

Abstract

Remote collaborative platforms increasingly integrate generative AI to support group ideation. These platforms are sociotechnical configurations in which spatial mediation, interaction modality, AI output format, and the mechanisms that make contributions visible to a group co-vary as properties of a deployed system. This paper examines how such configurations shape participants' collaboration and their engagement with AI during creative work. We report a comparative study of two commercially available platforms that instantiate contrasting configurations: a planar shared canvas with text-based AI integration, and an immersive virtual reality workspace with concise AI output embedded in the shared space. Fourteen all-women triads completed a structured ideation task consisting of human-only idea generation, AI-supported idea expansion, and group convergence. We analyzed collaboration patterns, selection of AI-generated ideas, perceived idea quality, workload, presence, and their lexical characteristics. The immersive configuration yielded greater spatial presence and introduced a participation paradox, in which spatial freedom enabled exploration and fragmented group coherence; it was also associated with more balanced role distribution during convergence, at the cost of higher physical demand. In both configurations, AI multiplied the idea pool, and ideas groups authored with AI available were rated above participants' own. AI output format: about 21 words per idea on the planar canvas and 3 in the immersive workspace. Tracked how participants evaluated AI-generated ideas and how often they selected them unaltered as finalists. Neither configuration made AI contributions visible or attributable to the group: participants invoked AI individually and asynchronously in both. We derive design implications for AI output format, group-visible AI invocation, and spatial support for convergence

Figures & tables

Explore similar work

Jul 29, 2026

AI as Friction for Reflection Support in Ideation

Generative AI tools for creative work tend to be designed around the goal of removing friction, on the assumption that smoother iteration and faster output translate into more value for the designer. We argue, however, that this framing leaves out something important about how design ideation works, namely reflection-in-action. The act of accepting, rejecting and reworking candidate ideas is both a path to a final outcome and the process through which designers develop the rationale that allows them to think with their ideas and to communicate them to others. This becomes particularly important in group ideation, where ideas need to be expressed and explained to others to allow the group to extend, reject or combine them further. We suggest that AI in design ideation might be more usefully thought of as a friction agent for reflection rather than as a smoothing agent for output. This reframing opens up a different role for AI in design ideation, one that supports designers in building and carrying rationale rather than substituting for it.
Oct 12, 2026

Good human thinking populates AI's semantic blind spots

AI-generated outputs tend to be more similar (homogenized) than human ideas. Does the human heterogeneity that extends beyond AI homogenization reflect valuable thinking that AI misses, or bad human ideas that AI avoids? We quantified how much an individual response expands an idea space beyond recurring clusters of ideas, enabling us to identify human responses located in AI's "semantic blind spots" (regions AI sparsely covers). Across three large samples (college admissions essays, alternative uses of objects, and interpersonal problem solving), human ideas in AI blind spots predicted higher academic achievement and performed as well or better on creativity, quality, and effectiveness. In contrast to humans, when AI expanded idea space, the association with creativity weakened or reversed. AI blind spots persisted across 66 diverse models and were not resolved by human-AI collaboration. Thinking "outside the bots" does not appear to reflect low-performing human variation that AI can safely omit.
Apr 9, 2026

Human-AI Collaboration Reconfigures Group Regulation from Socially Shared to Hybrid Co-Regulation

Generative AI (GenAI) is increasingly used in collaborative learning, yet its effects on how groups regulate collaboration remain unclear. Effective collaboration depends not only on what groups discuss, but on how they jointly manage goals, participation, strategy use, monitoring, and repair through co-regulation and socially shared regulation. We compared collaborative regulation between Human-AI and Human-Human groups in a parallel-group randomised experiment with 71 university students completing the same collaborative tasks with GenAI either available or unavailable. Focusing on human discourse, we used statistical analyses to examine differences in the distribution of collaborative regulation across regulatory modes, regulatory processes, and participatory focuses. Results showed that GenAI availability shifted regulation away from predominantly socially shared forms towards more hybrid co-regulatory forms, with selective increases in directive, obstacle-oriented, and affective regulatory processes. Participatory-focus distributions, however, were broadly similar across conditions. These findings suggest that GenAI reshapes the distribution of regulatory responsibility in collaboration and offer implications for the human-centred design of AI-supported collaborative learning.