PulseAugur
实时 08:43:45
English(EN) AgentKV: Phase-Aware KV Eviction for Agentic LLMs

AgentKV通过面向阶段的KV驱逐提高了LLM效率

研究人员开发了AgentKV,一种用于管理Agentic大型语言模型(LLM)中KV缓存的新方法。AgentKV解决了传统KV驱逐方法(依赖最近的token)未能考虑Agentic LLM在思考、行动和工具使用等不同阶段的多样化查询模式的问题。通过为每个阶段维护单独的查询缓冲区,AgentKV可以更有效地对相关缓存键进行评分和保留。与R-KV和Tri-attention等现有方法相比,这种方法提高了任务性能并增加了输出token吞吐量,在某些场景下甚至超过了全KV服务。 AI

影响 提高了LLM服务效率,可能支持更复杂的Agentic应用并降低计算成本。

排序理由 这是一篇详细介绍提高LLM效率的新颖方法的学术论文。 [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

AgentKV通过面向阶段的KV驱逐提高了LLM效率

本文如何被排名

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是一篇详细介绍提高LLM效率的新颖方法的学术论文。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Taowen Tony Liu, Jeffrey T. H. Wong, Can Xiao, Bowen Yang, Hao Mark Chen, Yiren Zhao ·

    AgentKV:面向Agentic LLM的阶段感知KV驱逐

    arXiv:2609.14872v1 Announce Type: cross Abstract: Agentic serving can consume orders of magnitude more tokens than chatbot workloads, stressing both KV-cache capacity and decode-time bandwidth. Most KV-eviction methods score cached keys against representative queries drawn from t…