arXiv cs.CL· Qingsen Ma, Dianyun Wang, Jiahong Liu, Irwin King·· 12 小时前AI 评分38
Parametric Session State：无需重放历史即可恢复检索意图的会话记忆层
Parametric Session States Recover Retrieval Intent without Replaying History
AI 导读
研究者提出 Parametric Session State（PSS），一种可复用的会话记忆层，能在不重放交互历史的情况下恢复检索意图，同时将事实性知识保留在外部。该方法针对长对话中“使用之前的配置”这类省略了项目、实体和版本词的后续请求，避免长上下文模型反复处理历史的开销，也弥补传统 RAG 假设查询信息充分的不足。论文编号 arXiv:2610.33047，归类 cs.CL 与 cs.AI。
正文
Abstract:Long-running assistants often interpret follow-up requests whose referents, constraints, and active goals were established many turns earlier. The central challenge is therefore not only context length, but retrieval intent: a current query such as ``use the previous configuration'' may omit the project, entity, and version terms needed to locate relevant evidence. Long-context models can recover those terms by replaying the interaction, but repeatedly pay the cost of processing history. Conventional retrieval-augmented generation (RAG) is cheaper, yet assumes an information-sufficient query; conversational rewriting either rereads the history or depends on an explicitly maintained textual memory. We introduce \emph{Parametric Session State} (\method{}), a reusable session-memory layer that remembers what to search for while keeping factual knowledge external.
| Comments: | RAG,long context |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33047 [cs.CL] |
| (or arXiv:2610.33047v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33047 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qingsen Ma [view email]
[v1]
Sat, 17 Oct 2026 05:07:32 UTC (31,854 KB)
来源：arXiv cs.CL · arxiv.org