Reproduce “Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Taufiq Daryanto, Xiaohan Ding, Kaike Ping, Lance T. Wilhelm, Yan Chen, Chris Brown, Eugenia H. Rho
This research introduces human-human-AI (HHAI) triadic programming, where an AI agent augments two human collaborators, to investigate if AI can reinforce collaborative learning without replacing human interaction. The study found that HHAI setups significantly restored collaborative learning and social presence while promoting more responsible AI engagement and maintaining comparable programming performance relative to human-AI dyadic programming.
Key insights
- Integrating AI into human-human collaboration restores critical collaborative learning and social presence, which are diminished in human-AI dyadic setups.
- The presence of a human partner fosters greater responsibility in understanding and applying AI suggestions, particularly in a shared AI context, mitigating over-reliance.
- Shared AI interventions that align with the conversational flow are less disruptive and more readily adopted than individual, potentially fragmented, personal AI suggestions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.