Search papers, labs, and topics across Lattice.
This paper introduces AgentForge, an immersive learning platform designed to enhance the skills of novice software engineers by simulating collaborative roles in a multi-agent code-repair workflow. The study reveals that participants, while engaging in specific roles such as Code Reviewer or Patch Author, demonstrated significant improvements in understanding software repair and agent collaboration, despite varying interaction demands across roles. Notably, the Code Reviewer role was identified as the most challenging, requiring more interaction and time, yet leading to the highest reported gains in knowledge and critical evaluation of AI outputs.
Novice developers using AgentForge significantly improved their software engineering skills and critical collaboration with AI, despite facing varying interaction challenges.
Agentic AI is increasingly used to coordinate planning, implementation, review, and testing in software development, yet it often offers limited transparency into its decisions and interactions. Many such systems also assume that users can effectively guide the AI's decisions and validate its outputs. This assumption poses a particular challenge for novices, who must simultaneously learn how agentic AI works, how to collaborate with it effectively, and how to evaluate its outputs critically. To address this challenge, we present \textit{AgentForge}, an immersive learning system in which novices take on one of four software-engineering roles: Task Planner, Patch Author, Code Reviewer, or Test Runner, within a multi-agent code-repair workflow. In each practice session, the novices perform their chosen role while AI agents perform the remaining three. Through role-based scaffolding and metacognitive support, AgentForge clarifies role-specific responsibilities, makes agent coordination and intermediate artifacts visible, and encourages novices to monitor and evaluate their decisions. In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support. However, interaction demands differed significantly across practices: the Code Reviewer practice required more interaction turns, reroutes, and completion time ($p_{\mathrm{adj}} = .004$) and was perceived as the most challenging. Participants nevertheless reported significant gains in their understanding of software repair and agent collaboration ($p_{\mathrm{adj}}<.001$). These findings suggest that AgentForge can help novices develop practical software-engineering skills while learning to collaborate with agentic AI more critically and effectively.
