Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations 事件

Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations arXiv:2604.12376v2 Announce Type: replace Abstract: When LLM conversations grow beyond the context window, old content must be evicted -- but how does the model recover it when needed? We propose cooperative paging: evicted segments are replaced with minimal keyword bookmarks ([pN:keywords], ~8-24 tokens each), and the model is given a recall() tool to retrieve full content on demand. On the LoCoMo benchmark (10