Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving
HEAR is established as a reusable coordination substrate for efficient agentic LLM serving by separating protocol semantics from optimization policies, and Mooncake shows that workflow intent and live engine state provide complementary benefits across load regimes.
Jia-Qi-Fu-Quan Zhao, Hao-Dong Chen, Jitai Hao et al.
· 0 citations