From Tool to Partner: Exploring the Roles of Embodiment on AI Agent in Pair Programming

Xiaoran Yang , Yang Zhan , Noboru Matsuda , Qiao Jin
VL/HCC '25: The IEEE Symposium on Visual Languages and Human-Centric Computing 2025 conference
🏆 Best Paper Honorable Mention
From Tool to Partner: Exploring the Roles of Embodiment on AI Agent in Pair Programming

Abstract

Pair programming with AI often faces challenges in productive communication and engagement. Integrating embodiment offers a promising solution by making AI a more engaging and context-aware programming partner. To explore how embodied AI agent supports programming learning and affects user experiences, we designed a virtual reality (VR) programming environment with Wizard-of-Oz-controlled AI agents. Our study collected data from 18 participants through knowledge acquisition assessments and interviews. The results showed that embodiment improved engagement, enhanced communication efficiency, and offered emotional support. Specifically, the incorporation of embodied actions allows users to perceive the AI agent as a programming partner and introduces many interactions that resemble those shared with real-life partners.

Summary

This study investigates what happens when an AI coding assistant gets a visible body in virtual reality instead of being just a text-based tool. Giving the AI a physical presence transformed how programmers related to it -- they communicated more naturally, felt more emotionally supported, and treated the AI more like a real collaborative partner than a utility.