Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization

ArXi:2605.19782v1 Announce Type: new LLM discovery and optimization systems are increasingly applied across domains, implementing a common propose-evaluate-revise loop. Such optimization or discovery progresses via context conditioning on received feedback from an environment. However, as modern LLM agents are increasingly complex in their structure, it is difficult to evaluate which components contribute the most, and when and how this exploration may fail. We answer these questions through three controlled experiments.