MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 62 references that are in the map. First posted on arXiv 15 Jun 2026.
Builds on
45 of 62 references.
References · 45
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
- 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
33 more
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
- 2021Improving language models by retrieving from trillions of tokenscited by 1,293
- 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
- 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
- 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
- 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
- 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
- 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 575
- 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
- 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 500
- 2023LaMP: When Large Language Models Meet Personalizationcited by 437
- 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 367
- 2023Augmenting Language Models with Long-Term Memorycited by 189
- 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
- 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 173
- 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 156
- 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 143
- 2025From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMscited by 124
- 2024Personalization of Large Language Models: A Surveycited by 104
- 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 92
- 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 78
- 2021D2S: Document-to-Slide Generation Via Query-Based Text Summarizationcited by 50
- 2023LayoutPrompter: Awaken the Design Ability of Large Language Modelscited by 48
- 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Modelscited by 41
- 2025A Survey of Personalization: From RAG to Agentcited by 27
- 2025SlideGen: Collaborative Multimodal Agents for Scientific Slide Generationcited by 25
- 2023LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Modelscited by 19
- 2026DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generationcited by 18
- 2025SlideTailor: Personalized Presentation Slide Generation for Scientific Paperscited by 13
- 2025DesignPref: Capturing Personal Preferences in Visual Design Generationcited by 7
- 2025SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentationscited by 5
- 2026Narrative-Driven Paper-to-Slide Generation via ArcDeckcited by 5
- 2026Agentic Tool Use in Large Language Modelscited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.