Agentic Education: Using Claude Code to Teach Claude Code

• URL: http://arxiv.org/abs/2604.17460v1
• Date: Sun, 19 Apr 2026 14:20:09 GMT
• Title: Agentic Education: Using Claude Code to Teach Claude Code
• Abstract summary: cc-selftrain is a modular interactive curriculum for learning Claude Code, an agentic AI coding tool, through hands-on project construction.<n>The system introduces five contributions: (1) a persona progression model that adapts instructor tone across four stages; (2) an adaptive learning system that observes engagement quality through hook-based scaffolding; and (3) a cross-domain unified curriculum in which five project domains share identical feature sequencing.<n>A pilot evaluation with 27 participants shows statistically significant reported self-efficacy gains across all 10 skill areas.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI coding assistants have proliferated rapidly, yet structured pedagogical frameworks for learning these tools remain scarce. Developers face a gap between tool documentation and practical mastery, relying on fragmented resources such as blog posts, video tutorials, and trial-and-error. We present cc-self-train, a modular interactive curriculum for learning Claude Code, an agentic AI coding tool, through hands-on project construction. The system introduces five contributions: (1) a persona progression model that adapts instructor tone across four stages (Guide, Collaborator, Peer, Launcher), operationalizing Gradual Release of Responsibility for AI-mediated instruction; (2) an adaptive learning system that observes engagement quality through hook-based heuristics and adjusts scaffolding at two timescales, using streak detection for mid-module intervention and aggregate metrics for module-boundary persona changes; (3) a cross-domain unified curriculum in which five distinct project domains share identical feature sequencing, enabling transfer learning; (4) a step-pacing mechanism with explicit pause primitives to manage information overload in an AI-as-instructor context; and (5) an auto-updating curriculum design in which the onboarding agent detects upstream tool changes and updates teaching materials before instruction begins. A parametrized test suite enforces structural consistency as a proxy for pedagogical invariants across all 50 modules. A pilot evaluation with 27 participants shows statistically significant reported self-efficacy gains across all 10 assessed skill areas (p < 0.001), with the largest effects on advanced features such as hooks and custom skills. We discuss implications for the design of auto-updating educational systems.

Related papers

• LearnAI: Just-in-Time AI Co-Creation Across Disciplines at a University [2.980329026942995]
  This report presents the LearnAI Framework, a two-layer model for just-in-time AI co-creation piloted at a comprehensive teaching university.<n>The Wide-Exposure Layer embeds short presentations in existing courses to build AI awareness at scale, reaching students and faculty across 18 courses in five disciplines.<n>The Customized Co-Creation Layer provides opt-in, one-on-one sessions where clients work with trained undergraduate tutors through a 5-Stage Pedagogical Script.<n>Interviews with five clients and two tutors suggest a recurring change in how clients described AI use, shifting from treating AI as a passive answer machine to engaging
  arXiv  Detail & Related papers  (2026-08-19T17:44:54Z)
• LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching [21.93366912657001]
  LectraAgents is a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching.<n>At its core, LectraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents.<n> Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches.
  arXiv  Detail & Related papers  (2026-06-15T09:03:12Z)
• MAIC-UI: Making Interactive Courseware with Generative UI [55.66338307665182]
  We present MAIC-UI, a zero-code authoring system that enables educators to create and rapidly edit interactive courseware.<n>MAIC-UI employs structured knowledge analysis with multi-modal understanding to ensure pedagogical rigor.
  arXiv  Detail & Related papers  (2026-04-28T16:15:04Z)
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization [61.37478254738943]
  Inference-time skill augmentation is fundamentally limited.<n>We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization.<n>SKILL0 achieves substantial improvements over the standard RL baseline.
  arXiv  Detail & Related papers  (2026-04-02T17:03:05Z)
• CurLL: A Developmental Framework to Evaluate Continual Learning in Language Models [6.333098807183056]
  We introduce a comprehensive continual learning dataset and benchmark (CurlL) grounded in human developmental trajectories from ages 5-10.<n>CurlL spans five developmental stages (0-4) covering ages 5-10, supported by a skill graph that breaks down broad skills into smaller abilities.<n>We generate a 23.4B-token synthetic dataset with controlled skill progression, vocabulary complexity, and format diversity.
  arXiv  Detail & Related papers  (2025-10-14T21:56:03Z)
• Cracking CodeWhisperer: Analyzing Developers' Interactions and Patterns During Programming Tasks [4.321456509547389]
  We investigate how developers engage with Amazon's CodeWhisperer, an LLM-based code-generation tool.<n>We conducted two user studies with two groups of 10 participants each.<n>We identify four behavioral patterns: 1) incremental code refinement, 2) explicit instruction using natural language comments, 3) baseline structuring with model suggestions, and 4) integrative use with external sources.
  arXiv  Detail & Related papers  (2025-10-13T15:22:12Z)
• CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning [80.18781219542016]
  Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.<n>Recent parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance.<n>We propose Cross-subspace Knowledge Alignment and Aggregation (CKAA) to enhance robustness against misleading task-ids.
  arXiv  Detail & Related papers  (2025-07-13T03:11:35Z)
• Design of AI-Powered Tool for Self-Regulation Support in Programming Education [4.171227316909729]
  Large Language Model (LLM) tools have demonstrated their potential to deliver high-quality assistance.<n>However, many of these tools operate independently from institutional Learning Management Systems.<n>This isolation limits the ability to leverage learning materials and exercise context for generating tailored, context-aware feedback.
  arXiv  Detail & Related papers  (2025-04-03T22:47:33Z)
• Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework [51.39847596489193]
  Bimanual robotic manipulation is an emerging and critical topic in the robotics community.<n>We propose a novel decoupled interaction framework that considers the characteristics of different tasks in bimanual manipulation.<n>Our framework achieves outstanding performance, with a 23.5% boost over the SOTA method.
  arXiv  Detail & Related papers  (2025-03-12T09:28:41Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• Empowering Private Tutoring by Chaining Large Language Models [87.76985829144834]
  This work explores the development of a full-fledged intelligent tutoring system powered by state-of-the-art large language models (LLMs) The system is into three inter-connected core processes-interaction, reflection, and reaction. Each process is implemented by chaining LLM-powered tools along with dynamically updated memory modules.
  arXiv  Detail & Related papers  (2023-09-15T02:42:03Z)

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.