Agentic LLMs for Microarchitecture Research: the Role of the Human Architect

Abstract summary

This study compares autonomous and human-guided language-model agents working on the same microarchitecture problem. With the model, initial designs and evaluation budget held fixed, expert feedback helps the agent redirect its search and improve on both its autonomous result and the reference design. The paper argues for an iterative collaboration in which architects inspect results and steer subsequent experiments.