MOOM：超长角色扮演对话中的记忆维护、组织与优化
MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues
AI总结：
针对超长角色扮演对话中记忆不受控增长的问题，提出双分支记忆插件MOOM，通过建模情节与角色并引入遗忘机制优化记忆管理，并构建ZH-4O数据集验证其优于现有方法。
摘要：
在人机角色扮演场景中，记忆提取对于维持连贯的超长对话至关重要。然而，现有方法常表现出不受控的记忆增长。为此，我们提出MOOM，这是首个双分支记忆插件，它利用文学理论，将情节发展与角色塑造建模为核心叙事元素。具体而言，一个分支跨多个时间尺度总结情节冲突，另一分支提取用户的角色画像。MOOM进一步整合了受“竞争-抑制”记忆理论启发的遗忘机制，以约束记忆容量并缓解不受控增长。此外，我们提出ZH-4O，一个专为角色扮演设计的中文超长对话数据集，其对话平均600轮，并包含人工标注的记忆信息。实验结果表明，MOOM优于所有最先进的记忆提取方法，在维持可控记忆容量的同时，所需的大语言模型调用次数更少。
英文摘要：
Memory extraction is crucial for maintaining coherent ultra-long dialogues in human-robot role-playing scenarios. However, existing methods often exhibit uncontrolled memory growth. To address this, we propose MOOM, the first dual-branch memory plugin that leverages literary theory by modeling plot development and character portrayal as core storytelling elements. Specifically, one branch summarizes plot conflicts across multiple time scales, while the other extracts the user's character profile. MOOM further integrates a forgetting mechanism, inspired by the ``competition-inhibition'' memory theory, to constrain memory capacity and mitigate uncontrolled growth. Furthermore, we present ZH-4O, a Chinese ultra-long dialogue dataset specifically designed for role-playing, featuring dialogues that average 600 turns and include manually annotated memory information. Experimental results demonstrate that MOOM outperforms all state-of-the-art memory extraction methods, requiring fewer large language model invocations while maintaining a controllable memory capacity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
