Oriel — AI & technology worth noticing, every day.

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Paper · https://arxiv.org/abs/2606.17162

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.

First seen by Oriel on .

AI summary

MemSlides is a hierarchical memory framework for personalized slide generation that separates persistent user preferences, session constraints, and reusable editing experience to support generation and local revision.

  • User profile memory stores intent-conditioned profiles for personalization during the initial generation round.
  • Working memory carries active preferences and session constraints across multi-turn revision.
  • Tool memory retains reusable execution experience, and its injection improved closed-loop modify behavior in diagnostic matched-pair settings.
  • Scoped slide-local revision targets the smallest affected region instead of regenerating the full deck.
  • Controlled experiments found improved persona-alignment judgments; working-memory carryover is illustrated through qualitative cases.

#presentation generation #agent memory #slide editing

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 174, latest observation ; 0 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 5, latest observation ; 0 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2606.17162https://arxiv.org/abs/2606.17162 Read discussion