Back to feed
arXiv cs.CL
arXiv cs.CL
6/17/2026
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

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

Short summary

MemSlides is a hierarchical memory framework for AI agents that personalize presentation generation by separating user profiles, session-level working memory, and reusable tool patterns. This architecture enables multi-turn revisions with precise local edits instead of full regeneration. Experiments validate improvements in persona alignment and editing reliability.

  • •Hierarchical memory system (user profile, working, tool) for personalized presentation agents
  • •Enables multi-turn revisions with localized editing instead of full-deck regeneration
  • •Experimental validation shows improved persona alignment and editing behavior

Generated with AI, which can make mistakes.

#ai-agents#research-breakthrough#ai-tools
Read full article at arXiv cs.CL

Is this a good recommendation for you?

Explore more

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
arXiv CS.AI
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
arXiv CS.AI
SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
arXiv CS.AI
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
arXiv cs.CL