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

2025-11-25

AI Summary

Contemporary personalized learning systems struggle to balance immediate responsiveness with long-term knowledge mastery—either relying on static curricula lacking adaptability or delivering fragmented content without goal-oriented, cumulative progression. This paper proposes a hybrid-driven learning framework that, for the first time, tightly integrates fine-grained dialogue memory modeling with goal-directed content generation. It continuously constructs a dynamic learner memory graph from everyday large language model interactions, enabling synergistic optimization of interest-awareness and mastery tracking. Technically, the framework unifies dialogue summarization, thematic planning, adaptive curriculum generation, and graph-structured progress monitoring into an end-to-end learning agent pipeline. A ten-participant user study confirms that the system generates content strongly aligned with recent learner activities and effectively uncovers knowledge gaps. Moreover, it reveals users’ emerging needs for learning consistency and agency over their educational trajectories.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Life-Long and Continual Learning
• Multiagent Systems: Multiagent Learning

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Personalizing learning with fixed curricula limits daily learner alignment
• Lightweight systems lack guidance toward long-term mastery goals
• Existing approaches fail to balance continuity with immediate learner needs

Innovation

• Infers learner needs from LLM conversations and memory graph
• Assembles coherent learning materials personalized to current needs
• Links concepts and surfaces gaps as scoped learning modules