| title | MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision |
|---|---|
| authors | Ye Jin, Yangyang Xu, Jun Zhu, Yibo Yang |
| date | 2026-06-15 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.17162 |
| upvotes | 34 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| primer | Memory for AI agents |
| abstract | Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term memory into user profile memory and tool memory. User profile memory stores intent-conditioned profiles for round-0 personalization, working memory carries active preferences and session constraints across revision rounds, and tool memory stores reusable execution experience for reliable localized editing. MemSlides pairs this memory design with scoped slide-local revision, so targeted updates act on the smallest affected region instead of repeatedly regenerating the full deck. In controlled experiments, user profile memory improves persona-alignment judgments on a multi-persona, multi-intent profile bank, tool-memory injection improves closed-loop modify behavior in diagnostic matched-pair settings, and qualitative cases illustrate working memory's ability to carryover preferences. Taken together, these results suggest that effective personalization in presentation authoring depends on separating persistent user profiles, session-level working memory, and reusable execution experience across generation and localized revision. |
cite
@misc{jin2026memslides,
title={MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision},
author={Ye Jin and Yangyang Xu and Jun Zhu and Yibo Yang},
year={2026},
eprint={2606.17162},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.17162}
}