Shang Wu

LACE: Large Language Model Aided Multi-Agent Framework for Agile RISC-V Instruction Extension

LACE is presented, an LLM-aided multi-agent workflow that translates natural-language ISAX intents into a compact two-level IR, performs retrieval-guided localized RTL edits over large repositories, and closes the loop with a compiler-agnostic riscv-formal checking flow.