Exploring Collaborative GenAI Agents in Synchronous Group Settings: Eliciting Team Perceptions and Design Considerations for the Future of Work

TL;DR

This paper investigates how collaborative GenAI agents can participate in synchronous group work using a mixed reality provotype with 25 professionals. Through speculative workshops and follow-up interviews, it reveals that such agents can enhance problem-solving by expanding perspectives and reducing social friction, but adoption hinges on trust, perceived usefulness, and organizational context. It also identifies design tensions around agent embodiment, prominence, and interaction modes in MR, and argues that MR can modulate GenAI influence through spatial and social cues. The work offers actionable guidance on governance, workflows, and responsible deployment to ensure AI augments rather than overrides team agency in the future of work.

Abstract

While generative artificial intelligence (GenAI) is finding increased adoption in workplaces, current tools are primarily designed for individual use. Prior work established the potential for these tools to enhance personal creativity and productivity towards shared goals; however, we don't know yet how to best take into account the nuances of group work and team dynamics when deploying GenAI in work settings. In this paper, we investigate the potential of collaborative GenAI agents to augment teamwork in synchronous group settings through an exploratory study that engaged 25 professionals across 6 teams in speculative design workshops and individual follow-up interviews. Our workshops included a mixed reality provotype to simulate embodied collaborative GenAI agents capable of actively participating in group discussions. Our findings suggest that, if designed well, collaborative GenAI agents offer valuable opportunities to enhance team problem-solving by challenging groupthink, bridging communication gaps, and reducing social friction. However, teams' willingness to integrate GenAI agents depended on its perceived fit across a number of individual, team, and organizational factors. We outline the key design tensions around agent representation, social prominence, and engagement and highlight the opportunities spatial and immersive technologies could offer to modulate GenAI influence on team outcomes and strike a balance between augmentation and agency.

Figures (11)

• Figure 1: Our Mixed Reality provotype showcased one possible future where teams share their physical space with collaborative GenAI agents (Left) that could actively participate in a deliberative group discussion (Right).
• Figure 2: An overview of our methods that included a speculative design workshop as well as individual follow-up interviews with teams. The team workshops employed a mix of methods including speculative ideation and reflection, embodied interactions with GenAI agents through an MR provotype, and a participatory design activity where participants used Lego blocks to depict their ideal GenAI-based collaborative agents.
• Figure 3: Our MR provotype included a shared 3D artifact of a city as well as a non-interactive virtual whiteboard. Agent contributions were generated through a GPT-based pipeline and their social behaviors were controlled through a Wizard-of-Oz interface (A). Agents could proactively indicate a desire to contribute by raising it's hand (B), and users could use MR buttons to engage in a private sidechannel with one agent (C).
• Figure 4: Images from our speculative team workshops where teams work on their individual worksheets (A), experience a group discussion with collaborative GenAI agents in Mixed Reality (B), and participate in our Lego Assembly Line activity to design their ideal collaborative agents (C).
• Figure 5: Example Lego agents our participants built to depict their ideal collaborative GenAI agent during our team workshops. Different colored Lego blocks were used to represent a variety of design dimensions.