AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering

• URL: http://arxiv.org/abs/2608.04148v1
• Date: Tue, 04 Aug 2026 18:58:18 GMT
• Title: AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering
• Abstract summary: We present textitAgentForge, an immersive learning system in which novices take on one of four software-engineering roles.<n>In each practice session, novices perform their chosen role while AI agents perform the remaining three.<n>In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support.
• Score: 4.609790123179083
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• "I'm Not Reading All of That": Understanding Software Engineers' Level of Cognitive Engagement with Agentic Coding Assistants [9.74467739744379]
  Over-reliance on AI systems can undermine users' critical thinking and promote complacency.<n>In software engineering, agentic coding assistants (ACAs) are rapidly becoming embedded in everyday development.
  arXiv  Detail & Related papers  (2026-03-15T05:03:20Z)
• AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios [49.90735676070039]
  The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow.<n>We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks.<n>We propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks.
  arXiv  Detail & Related papers  (2026-01-28T13:49:18Z)
• Exploring Human-AI Collaboration Using Mental Models of Early Adopters of Multi-Agent Generative AI Tools [4.382163871275696]
  We investigated how early adopters and developers conceptualize multi-agent Gen AI tools.<n>We conducted semi-structured interviews with 13 developers, all early adopters of multi-agent Gen AI technology who work at Microsoft.<n>We identified key challenges, including error propagation, unpredictable and unproductive agent loop behavior, and the need for clear communication to mitigate the layered transparency issues.
  arXiv  Detail & Related papers  (2025-09-10T05:35:38Z)
• How Software Engineers Engage with AI: A Pragmatic Process Model and Decision Framework Grounded in Industry Observations [1.516251872371896]
  GitHub Copilot and ChatGPT have given rise to "vibe coding"<n>This paper presents two complementary contributions.<n>First, a pragmatic process model capturing real-world AI-assisted SE activities, including prompt design, inspection, fallback, and refinement.<n>Second, a 2D decision framework that could help developers reason about trade-offs between effort saved and output quality.
  arXiv  Detail & Related papers  (2025-07-23T21:00:21Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
  We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities [117.49715661395294]
  Data structurization can play a promising role by transforming intricate and disorganized data into well-structured forms.<n>This survey presents a first systematic review of how graphs can empower AI agents.
  arXiv  Detail & Related papers  (2025-06-22T12:59:12Z)
• Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support [36.082282294551405]
  We introduce and evaluate Codellaborator, a design probe agent that initiates programming assistance based on editor activities and task context.<n>We find that proactive agents increase efficiency compared to prompt-only paradigm, but also incur workflow disruptions.
  arXiv  Detail & Related papers  (2025-02-25T21:37:25Z)
• TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks [55.03911355902567]
  We introduce TheAgentCompany, a benchmark for evaluating AI agents that interact with the world in similar ways to those of a digital worker.<n>We find that the most competitive agent can complete 30% of tasks autonomously.<n>This paints a nuanced picture on task automation with simulating LM agents in a setting a real workplace.
  arXiv  Detail & Related papers  (2024-12-18T18:55:40Z)
• Experiential Co-Learning of Software-Developing Agents [83.34027623428096]
  Large language models (LLMs) have brought significant changes to various domains, especially in software development. We introduce Experiential Co-Learning, a novel LLM-agent learning framework. Experiments demonstrate that the framework enables agents to tackle unseen software-developing tasks more effectively.
  arXiv  Detail & Related papers  (2023-12-28T13:50:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.