SOURCE-LINKED INTELLIGENCE

RoofLang: Enabling AI-Driven Architecting of LLM Inference Systems

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

AI is beginning to make substantive contributions to LLM inference optimization. Existing AI optimizations are predominantly profiling-based. Profiling-bound feedback confines the search to the capabilities and performance of an existing software stack, preventing a fundamentally better architecture of LLM inference systems from being identified. To enable the AI-driven LLM inference system architecting loop, we argue that a general workload representation, a verifiable mutation space, and an implementation-independent evaluator are required. We present the RoofLang domain-specific language (D

Read original source ↗ Open in workspace

recordType

paper

region

Global