Research

Paper

AI LLM February 19, 2026

Exploring The Impact Of Proactive Generative AI Agent Roles In Time-Sensitive Collaborative Problem-Solving Tasks

Authors

Anirban Mukhopadhyay, Kevin Salubre, Hifza Javed, Shashank Mehrotra, Kumar Akash

Abstract

Collaborative problem-solving under time pressure is common but difficult, as teams must generate ideas quickly, coordinate actions, and track progress. Generative AI offers new opportunities to assist, but we know little about how proactive agents affect the dynamics of real-time, co-located teamwork. We studied two forms of proactive support in digital escape rooms: a facilitator agent that offered summaries and group structures, and a peer agent that proposed ideas and answered queries. In a within-subjects study with 24 participants, we compared group performance and processes across three conditions: no AI, peer, and facilitator. Results show that the peer agent occasionally enhanced problem-solving by offering timely hints and memory support; however, it also disrupted flow, increased workload, and created over-reliance. In comparison, the facilitator agent provided light scaffolding but had a limited impact on outcomes. We provide design considerations for proactive generative AI agents based on our findings.

Metadata

arXiv ID: 2602.17864
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-02-19
Fetched: 2026-02-23 05:33

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17864v1</id>\n    <title>Exploring The Impact Of Proactive Generative AI Agent Roles In Time-Sensitive Collaborative Problem-Solving Tasks</title>\n    <updated>2026-02-19T21:59:33Z</updated>\n    <link href='https://arxiv.org/abs/2602.17864v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17864v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Collaborative problem-solving under time pressure is common but difficult, as teams must generate ideas quickly, coordinate actions, and track progress. Generative AI offers new opportunities to assist, but we know little about how proactive agents affect the dynamics of real-time, co-located teamwork. We studied two forms of proactive support in digital escape rooms: a facilitator agent that offered summaries and group structures, and a peer agent that proposed ideas and answered queries. In a within-subjects study with 24 participants, we compared group performance and processes across three conditions: no AI, peer, and facilitator. Results show that the peer agent occasionally enhanced problem-solving by offering timely hints and memory support; however, it also disrupted flow, increased workload, and created over-reliance. In comparison, the facilitator agent provided light scaffolding but had a limited impact on outcomes. We provide design considerations for proactive generative AI agents based on our findings.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-02-19T21:59:33Z</published>\n    <arxiv:comment>Published in Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI'26)</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Anirban Mukhopadhyay</name>\n    </author>\n    <author>\n      <name>Kevin Salubre</name>\n    </author>\n    <author>\n      <name>Hifza Javed</name>\n    </author>\n    <author>\n      <name>Shashank Mehrotra</name>\n    </author>\n    <author>\n      <name>Kumar Akash</name>\n    </author>\n    <arxiv:doi>10.1145/3772318.3791592</arxiv:doi>\n    <link href='https://doi.org/10.1145/3772318.3791592' rel='related' title='doi'/>\n  </entry>"
}