BOOKMARKS: Efficient Active Storyline Memory for Role-playing
Quick Answer
The BOOKMARKS framework enhances role-playing agents' memory by actively managing task-relevant bookmarks, significantly outperforming traditional methods with improved detail retention and efficiency.
Quick Take
The BOOKMARKS framework enhances role-playing agents' memory by actively managing task-relevant bookmarks, significantly outperforming traditional methods with improved detail retention and efficiency. It demonstrates superior performance on 85 characters from 16 artifacts, showcasing the effectiveness of search-based memory systems.
Key Points
- BOOKMARKS actively initializes and updates bookmarks for role-playing tasks.
- It outperforms traditional memory methods in retaining important details.
- The framework supports concept, behavior, and state searches.
- Demonstrated effectiveness across 85 characters from 16 artifacts.
- Offers both active grounding and passive updating for efficiency.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2605. 14169v1 Announce Type: new Abstract: 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.