MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision
arXiv: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 profile
The proliferation of language models and increasing user demand for personalized, automated content creation is driving innovation in agent frameworks.
This development represents a step towards more capable and personalized AI agents, reducing the need for direct human intervention in content generation and revision.
AI agents are transitioning from single-turn, prompt-response systems to multi-turn, memory-augmented frameworks that can learn and adapt to user preferences over time.
- · AI software developers
- · Content creators
- · SaaS platforms
- · Knowledge workers
- · Template-based presentation software
- · Generic content generation tools
AI agents will become more adept at personalized content creation, handling complex revision processes autonomously.
The increasing sophistication of memory-driven agents could lead to new forms of human-computer interaction and collaboration.
As agents learn and retain complex user profiles, ethical considerations around data privacy and the potential for manipulation will become more pronounced.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL