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
MemSlides：一种用于个性化幻灯片生成及多轮局部修订的分层记忆驱动智能体框架
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.
个性化演示文稿的生成不仅仅依赖于当前的提示词或模板：智能体必须在不同任务间保持稳定的用户偏好，在多轮修订过程中保留新引入的偏好和约束，并可靠地执行局部编辑。
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.
我们提出了 MemSlides，这是一种用于个性化演示智能体的分层记忆框架。该框架将长期记忆与工作记忆分离，并进一步将长期记忆划分为用户画像记忆（User Profile Memory）和工具记忆（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.
用户画像记忆存储用于初始轮次（round-0）个性化的意图条件画像，工作记忆在修订轮次间传递活跃偏好和会话约束，而工具记忆则存储可复用的执行经验，以实现可靠的局部编辑。
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.
MemSlides 将这种记忆设计与范围限定的幻灯片局部修订相结合，使得针对性的更新能够作用于受影响的最小区域，而非重复生成整个幻灯片文档。
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.
在对照实验中，用户画像记忆提升了在多角色、多意图画像库上的角色对齐判断能力；工具记忆注入改善了诊断匹配对设置下的闭环修改行为；定性案例则展示了工作记忆在延续用户偏好方面的能力。
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.
综上所述，这些结果表明，演示文稿创作中的有效个性化依赖于将持久的用户画像、会话级工作记忆以及可复用的执行经验在生成和局部修订过程中进行有效分离。