AI RESEARCH

LiteCoOp: Lightweight Multi-LLM Shared-Tree Reasoning for Model-Serving Compiler Optimizations

arXiv CS.AI

ArXi:2602.01935v2 Announce Type: replace-cross LLM-guided compiler optimization has recently shown promise, but existing approaches rely on a single large LLM throughout search, making them expensive and excluding smaller models. We pose the research question: whether heterogeneous LLMs can collaborate during compiler optimization while reducing compilation cost below optimization guided by a single large LLM. Crucially, this must be achieved without