When Workout Buddies Are Virtual: AI Agents and Human Peers in a Longitudinal Physical Activity Study
Alessandro Silacci, Mauro Cherubini, Arianna Boldi, Amon Rapp, Maurizio Caon
Abstract
Physical inactivity remains a critical global health issue, yet scalable strategies for sustained motivation are scarce. Conversational agents designed as simulated exercising peers (SEPs) represent a promising alternative, but their long-term impact is unclear. We report a six-month randomized controlled trial (N=280) comparing individuals exercising alone, with a human peer, or with a large language model-driven SEP. Results revealed a partnership paradox: human peers evoked stronger social presence, while AI peers provided steadier encouragement and more reliable working alliances. Humans motivated through authentic comparison and accountability, whereas AI peers fostered consistent, low-stakes support. These complementary strengths suggest that AI agents should not mimic human authenticity but augment it with reliability. Our findings advance human-agent interaction research and point to hybrid designs where human presence and AI consistency jointly sustain physical activity.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 57fcba46-b404-4d9c-8891-f67aa6cd5030Builds on10
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
- Towards Understanding Sycophancy in Language ModelsMrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud et al.ICLR 2024 · 762 citations
- Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily AssistantGaole He, Gianluca Demartini, Ujwal GadirajuCHI 2025 · 91 citations
- GPTCoach: Towards LLM-Based Physical Activity CoachingMatthew Jörke, Shardul Sapkota, Lyndsea Warkenthien, Niklas Vainio et al.CHI 2025 · 89 citations
- Changes in Research Ethics, Openness, and Transparency in Empirical Studies between CHI 2017 and CHI 2022Kavous Salehzadeh Niksirat, Lahari Goswami, Pooja Rao S. B., James Tyler et al.CHI 2023 · 43 citations
Related papers
- Large Language Model Agents for Improving Engagement with Behavior Change Interventions: Application to Digital MindfulnessHarsh Kumar, Suhyeon Yoo, Angela M. Zavaleta Bernuy, Jiakai Shi et al.CSCW 2025 · 7 citations
- ComPeer: A Generative Conversational Agent for Proactive Peer SupportTianjian Liu, Hongzheng Zhao, Yuheng Liu, Xingbo Wang et al.UIST 2024 · 27 citations
- Solitary Jogging with A Virtual Runner using SmartglassesTakeo Hamada, Ari Hautasaari, Michiteru Kitazaki, Noboru KoshizukaIEEE VR 2022 · 16 citations
- Personalization Paradox in Behavior Change Apps: Lessons from a Social Comparison-Based Personalized App for Physical ActivityJichen Zhu, Diane H. Dallal, Robert C. Gray, Jennifer Villareale et al.CSCW 2021 · 32 citations
- Supporting Effective Goal Setting with LLM-Based ChatbotsMichel Schimpf, Sebastian Maier, Anton Wyrowski, Lara Christoforakos et al.CHI 2026 · 2 citations
