{"slug": "memslides-a-hierarchical-memory-driven-agent-framework-for-personalized-slide", "title": "MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision", "summary": "Researchers propose MemSlides, a hierarchical memory framework for personalized presentation generation that separates long-term user profiles, session-level working memory, and reusable tool memory to enable stable personalization and reliable local edits across multi-turn revisions. Controlled experiments show improvements in persona alignment, closed-loop modification, and preference carryover, suggesting effective personalization depends on distinct memory components for generation and localized revision.", "body_md": "arXiv:2606.17162v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/memslides-a-hierarchical-memory-driven-agent-framework-for-personalized-slide", "canonical_source": "https://arxiv.org/abs/2606.17162", "published_at": "2026-06-17 04:00:00+00:00", "updated_at": "2026-06-17 04:26:32.381705+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "natural-language-processing", "ai-research"], "entities": ["MemSlides", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/memslides-a-hierarchical-memory-driven-agent-framework-for-personalized-slide", "markdown": "https://wpnews.pro/news/memslides-a-hierarchical-memory-driven-agent-framework-for-personalized-slide.md", "text": "https://wpnews.pro/news/memslides-a-hierarchical-memory-driven-agent-framework-for-personalized-slide.txt", "jsonld": "https://wpnews.pro/news/memslides-a-hierarchical-memory-driven-agent-framework-for-personalized-slide.jsonld"}}