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

arXiv: https://arxiv.org/abs/2605.27389 · HTML: https://mlsanity.com/paper/2605.27389/

## Key facts

- Cited by 1 papers 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 (most cited first, 6 of 6)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles](https://mlsanity.com/paper/2510.07925/) (2025)
- [A4L: An Architecture for AI-Augmented Learning](https://mlsanity.com/paper/2505.06314/) (2025)
- [Evolution of A4L: A Data Architecture for AI-Augmented Learning](https://mlsanity.com/paper/2511.11877/) (2025)
- [Evaluating Learner Representations for Differentiation Prior to Instructional Outcomes](https://mlsanity.com/paper/2604.05848/) (2026)

## Built on by (most cited first, 1 of 1)

- [Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs](https://mlsanity.com/paper/2606.10736/) (2026)

## 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.