AI RESEARCH
Improving Coherence and Persistence in Agentic AI for System Optimization
arXiv CS.AI
•
ArXi:2603.21321v1 Announce Type: new Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they struggle with complex system problems due to two critical failure modes: evolutionary neighborhood bias and the coherence ceiling. Evolutionary methods often remain trapped in local optima by relying on scalar benchmark scores, failing when coordinated multi-step changes are required.