---
id: 20261028-T0-14
title: "SLICE-Mem：用显著性门控给LLM智能体记忆做轻量整理，降低推理开销"
title_en: "SLICE-Mem Cuts LLM Agent Memory Cost With Salience-Gated Curation"
url: https://ai.daily.yangsir.net/daily/20261028-T0-14
issue_date: 2026-10-28
publish_date: 2026-10-27T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2610.33015
---

# SLICE-Mem：用显著性门控给LLM智能体记忆做轻量整理，降低推理开销

arXiv新论文提出SLICE-Mem，针对LLM智能体长期记忆成本高的问题。现有方案在记忆的准入、提取和组织环节反复调用LLM推理，带来可观的费用和延迟。SLICE-Mem用显著性门控做轻量级信息整理，减少不必要的模型调用，同时维持个性化、时间连贯的交互记忆。论文称该方法在效率上有改善，但具体的成本下降幅度和基准对比需查看全文。适合关注长记忆智能体落地成本的团队参考。

## English Version

**SLICE-Mem Cuts LLM Agent Memory Cost With Salience-Gated Curation**

A new arXiv paper presents SLICE-Mem to address the cost of long-term memory in LLM agents. Existing approaches repeatedly invoke LLM inference for memory admission, extraction, and organization, adding cost and latency. SLICE-Mem applies salience-gated lightweight curation to cut unnecessary model calls while maintaining personalized, temporally coherent interaction memory. The paper reports efficiency gains, though exact cost reductions and benchmark comparisons require the full text. Relevant to teams weighing deployment costs for long-memory agents.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2610.33015)

**详情页**：https://ai.daily.yangsir.net/daily/20261028-T0-14

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*