mlsanityData to 14 Oct 2026

Memory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in Stateful Personalization

arXiv 2605.27389 ↗First posted 14 Apr 2026cs.IR cs.AI cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

We study how conditioning context shapes personalization behavior in a teacher-facing educational recommender system. We compare contextual conditioning based on the current student question with memory-based conditioning using persistent learner information. Using deviation correlation and paired statistical tests, we find that contextual recommendations exhibit stronger question-level responsiveness, while memory-based recommendations exhibit history-dependent behaviors, including learner-specific differentiation under identical input. Teacher-facing evaluation signals suggest these recommendations are interpretable and actionable. These results indicate that embedding-based similarity metrics capture responsiveness to the current question but do not characterize personalization grounded in learner history, motivating behavior-level diagnostics for studying conditioning effects.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 6 of its 22 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

6 of 22 references.

References · 6

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  3. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profilescited by 17
  4. 2025A4L: An Architecture for AI-Augmented Learningcited by 4
  5. 2025Evolution of A4L: A Data Architecture for AI-Augmented Learningcited by 4
  6. 2026Evaluating Learner Representations for Differentiation Prior to Instructional Outcomescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.