Topic: unified memory

1 stories found

Monday, August 24, 2026

research35

Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified Memory

Nexus introduces a depth-adaptive key-value cache and retrieval-decoupled tool routing to improve the efficiency of agentic large language models operating on the Model Context Protocol, addressing the issue of prefill time dominating due to growing tool registries. This innovation aims to reduce time-to-first-token (TTFT) by re-encoding fewer tool schemas each turn.

arxiv.orgโ†—

๐ŸŒฟ That's all for now. Come back tomorrow.

1 of 1 items shown. Sources: 107 days indexed.