MOOM通过双分支机制实现角色扮演长对话的可控记忆管理
MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues
- 用双分支结构分别提取情节冲突与用户角色画像
- 在600回合中文长对话上实现更少调用次数与可控内存增长
- 适合需要长期记忆维护的角色扮演系统开发者
在人机角色扮演的超长对话中，记忆提取对保持连贯性至关重要。现有方法常出现记忆无控制增长问题。为此，我们提出MOOM，首个基于文学理论的双分支记忆插件，将情节发展与人物塑造作为核心叙事元素建模。一个分支在多时间尺度上总结情节冲突，另一个分支提取用户角色画像。MOOM还引入受‘竞争抑制’记忆理论启发的遗忘机制，以限制记忆容量并缓解无序增长。此外，我们构建了ZH-4O数据集，专为角色扮演设计的中文超长对话数据集，平均对话轮次达600轮，包含人工标注的记忆信息。实验表明，MOOM优于所有当前最优记忆提取方法，在减少大语言模型调用次数的同时维持可控的内存容量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。