LOOM: Personalized Learning Informed by Daily LLM Conversations Toward Long-Term Mastery via a Dynamic Learner Memory Graph

TL;DR

LOOM is a personalized learning system that dynamically adapts to learners' evolving needs by integrating recent conversations and a learner memory graph, balancing immediate relevance with long-term mastery.

Contribution

It introduces LOOM, a novel agentic pipeline combining conversation analysis and a dynamic learner graph to personalize and guide learning trajectories.

Findings

Participants found LOOM's lessons relevant and gap-identifying.

LOOM effectively links concepts and tracks progress.

Users desired more consistency and control.

Abstract

Foundation models are increasingly used to personalize learning, yet many systems still assume fixed curricula or coarse progress signals, limiting alignment with learners' day-to-day needs. At the other extreme, lightweight incidental systems offer flexible, in-the-moment content but rarely guide learners toward mastery. Prior work privileges either continuity (maintaining a plan across sessions) or initiative (reacting to the moment), not both, leaving learners to navigate the trade-off between recency and trajectory-immediate relevance versus cumulative, goal-aligned progress. We present LOOM, an agentic pipeline that infers evolving learner needs from recent LLM conversations and a dynamic learner memory graph, then assembles coherent learning materials personalized to the learner's current needs, priorities, and understanding. These materials link adjacent concepts and surface gaps as tightly scoped modules that cumulatively advance broader goals, providing guidance and sustained progress while remaining responsive to new interests. We describe LOOM's end-to-end architecture and working prototype, including conversation summarization, topic planning, course generation, and graph-based progress tracking. In a formative study with ten participants, users reported that LOOM's generated lessons felt relevant to their recent activities and helped them recognize knowledge gaps, though they also highlighted needs for greater consistency and control. We conclude with design implications for more robust, mixed-initiative learning pipelines that integrate structured learner modelling with everyday LLM interactions.