Patches that pass local tests can still fail a live server: SWE-Serve puts the gap near one in three
AI coding agents that change inference-serving software can pass local tests yet fail when a server loads a real model and handles requests. SWE-Serve turns 83 merged SGLang changes into 53 executable tasks, 19 of which start a live server. On those 19 tasks, the same 627 patches pass 69.4% of the time without the live-serving checks and 45.9% with the complete verifier, so about one in three otherwise-passing patches fails live serving.