MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision
Quick Answer
MemSlides introduces a hierarchical memory framework for personalized presentation generation, enhancing user preference retention and localized editing.
Quick Take
MemSlides introduces a hierarchical memory framework for personalized presentation generation, enhancing user preference retention and localized editing. It separates long-term memory into user profile and tool memory, improving persona alignment and modification behavior in experiments, suggesting effective personalization relies on distinct memory types.
Key Points
- MemSlides separates long-term memory into user profile and tool memory for better personalization.
- Working memory retains active preferences across multi-turn revisions for reliable edits.
- Controlled experiments show improved persona alignment and modification behavior.
- Localized updates target specific slide areas instead of regenerating entire decks.
- Effective presentation authoring relies on distinct memory types for user preferences.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 17162v1 Announce Type: new 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.