Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming

2023-06-08 · Qianou Ma, Tongshuang Wu, Kenneth Koedinger

The emergence of large-language models (LLMs) that excel at code generation and commercial products such as GitHub's Copilot has sparked interest in human-AI pair programming (referred to as "pAIr programming") where an AI system collaborates with a human programmer. While traditional pair programming between humans has been extensively studied, it remains uncertain whether its findings can be applied to human-AI pair programming. We compare human-human and human-AI pair programming, exploring their similarities and differences in interaction, measures, benefits, and challenges. We find that the effectiveness of both approaches is mixed in the literature (though the measures used for pAIr programming are not as comprehensive). We summarize moderating factors on the success of human-human pair programming, which provides opportunities for pAIr programming research. For example, mismatched expertise makes pair programming less productive, therefore well-designed AI programming assistants may adapt to differences in expertise levels.

📄 PDF Abstract BibTeX arXiv:2306.05153

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learning

2026-01-17 · Taufiq Daryanto, Xiaohan Ding, Kaike Ping, Lance T. Wilhelm 외 arxiv

As AI assistance becomes embedded in programming practice, researchers have increasingly examined how these systems help learners generate code and work more efficiently. However, these studies often position AI as a rep…

The Collaboration Gap in Human-AI Work

2026-04-20 · Varad Vishwarupe, Marina Jirotka, Nigel Shadbolt, Ivan Flechais arxiv

LLMs are increasingly presented as collaborators in programming, design, writing, and analysis. Yet the practical experience of working with them often falls short of this promise. In many settings, users must diagnose m…

Collaborating with Humans without Human Data

2021-10-15 · NeurIPS 2021 12 · DJ Strouse, Kevin R. McKee, Matt Botvinick, Edward Hughes 외

Collaborating with humans requires rapidly adapting to their individual strengths, weaknesses, and preferences. Unfortunately, most standard multi-agent reinforcement learning techniques, such as self-play (SP) or popula…

Multi-agent Reinforcement Learning

Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmers

2024-04-16 · Ahmed E. Hassan, Gustavo A. Oliva, Dayi Lin, Boyuan Chen 외

The advent of Foundation Models (FMs) and AI-powered copilots has transformed the landscape of software development, offering unprecedented code completion capabilities and enhancing developer productivity. However, the …

Code Completion Decision Making Self-Learning

BCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordination

2024-08-15 · Xin Hao, Bahareh Nakisa, Mohmmad Naim Rastgoo, Richard Dazeley 외

Deep reinforcement Learning (DRL) offers a powerful framework for training AI agents to coordinate with human partners. However, DRL faces two critical challenges in human-AI coordination (HAIC): sparse rewards and unpre…

AI Agent Deep Reinforcement Learning Reinforcement Learning (RL)