BOOKMARKS：用於角色扮演的高效主動故事線記憶

摘要

记忆系统对于角色扮演代理（RPA）维持长期一致性至关重要。然而，现有的RPA记忆方法（如特征刻画）主要依赖循环摘要，其压缩过程不可避免地丢弃了重要细节。为解决此问题，我们提出一种基于搜索的记忆框架——BOOKMARKS，该框架主动为当前任务（如角色扮演）初始化、维护并更新任务相关的书签片段。书签被结构化为故事线中特定时间点上某个问题的答案。针对每个当前任务，BOOKMARKS会选择可复用的现有书签，或通过有用问题初始化新书签（在故事起始处）。随后将这些书签同步至当前故事节点，并相应更新其答案，从而使其在未来的定位轮次中高效复用。与循环摘要相比，BOOKMARKS具备以下优势：（1）主动定位以捕捉任务特定细节；（2）被动更新以避免不必要的计算。在实现层面，BOOKMARKS支持概念搜索、行为搜索和状态搜索，每种搜索均由高效的同步方法驱动。基于来自16个作品中的85个角色，BOOKMARKS显著优于现有RPA记忆基线方法，验证了基于搜索的记忆框架对RPA的有效性。

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.