用搜索式书签记忆，让角色扮演更连贯精准。
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
- 以问答形式存关键剧情点，动态管理角色记忆
- 在16个作品85个角色上显著超越现有方法
- 适合需要长期一致性的人工智能角色系统
记忆系统对角色扮演智能体（RPAs）保持长程一致性至关重要。现有方法（如人物画像）依赖循环摘要，压缩过程会丢失重要细节。为此，我们提出基于搜索的记忆框架BOOKMARKS，主动初始化、维护并更新当前任务（如角色表演）相关的剧情书签。书签是特定剧情节点上的问题答案。每个任务中，BOOKMARKS选择可复用的旧书签或在剧情起点创建新书签，通过高效同步机制将书签对齐至当前故事点，并更新答案，便于后续任务快速调用。相比循环摘要，BOOKMARKS实现（1）主动定位任务相关细节，（2）被动更新避免冗余计算。系统支持概念、行为和状态三种搜索，每种均配备高效同步方法。在16个作品中的85个角色上，BOOKMARKS显著优于现有基准，验证了搜索式记忆的有效性。
原文摘要 · Abstract (English)
Memory systems are critical for role-playing agents (RPAs) to maintain long-horizon consistency. However, existing RPA memory methods (e.g., profiling) mainly rely on recurrent summarization, whose compression inevitably discards important details. To address this issue, we propose a search-based memory framework called BOOKMARKS, which actively initializes, maintains, and updates task-relevant pieces of bookmarks for the current task (e.g., character acting). A bookmark is structured as the answer to a question at a specific point in the storyline. For each current task, BOOKMARKS selects reusable existing bookmarks or initializes new ones (at storyline beginning) with useful questions. These bookmarks are then synchronized to the current story point, with their answers updated accordingly, so they can be efficiently reused in future grounding rounds. Compared with recurrent summarization, BOOKMARKS offers (1) active grounding for capturing task-specific details and (2) passive updating to avoid unnecessary computation. In implementation, BOOKMARKS supports concept, behavior, and state searches, each powered by an efficient synchronization method. BOOKMARKS significantly outperforms RPA memory baselines on 85 characters from 16 artifacts, demonstrating the effectiveness of search-based memory for RPAs.
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。