YT-Pilot: Turning YouTube into Structured Learning Pathways with Context-Aware AI Support

Abstract

YouTube is widely used for informal learning, where learners explore lectures and tutorials without a predefined curriculum. However, learning across videos remains fragmented: learners must decide what to watch, how videos relate, and how knowledge builds. Existing tools provide partial support but treat planning and learning as separate activities, lacking a persistent interaction structure that connects them. Grounded in self-regulated learning theory (SRLT), we introduce YT-Pilot, a pathway-aware learning system that operationalizes the learning pathway as a persistent, user-facing interaction structure spanning planning and learning. The pathway coordinates goal setting, planning, navigation, progress tracking, and cross-video assistance. Through a within-subjects study ($N=20$), we show that YT-Pilot significantly improves perceived goal clarity, pathway coherence, and progress tracking, while shifting interaction toward pathway-level reasoning across multiple resources.

Figures (8)

• Figure 1: System architecture for YT-Pilot across planning (left) and learning (right) phases, with applied theories in yellow.
• Figure 2: Concept preview enables learners to specify learning goals and preferences, then inspect an AI-generated concept map that provides a high-level, conceptual breakdown of the topic before pathway generation.
• Figure 3: Pathway review presents a structured multi-week learning plan with ordered videos, learning objectives, and per-video rationales to help learners understand and revise the generated pathway before starting.
• Figure 4: Learning environment for video study includes: (a) concept map and generated learning pathway (top), (b) main learning space that integrates the instructional video, pathway-aware conversational guidance, key terms, and a context-based note-taking panel to support focused learning within a structured pathway (bottom).
• Figure 5: Overview of YouTube Learning workflow. A user enters a query to generate topic-based video groupings organized into categories. Learners browse and select videos from these grouped sections and watch them in the video interface, where a single-video AI assistant provides support during viewing.