Component-Aware Feedback for Self-Evolving Programs
LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which component edits produced which fitness metric changes. Existing methods force the mutator LLM to infer the effect of prior edits from cluttered histories, maki...
Ethan Lin, Jinming Nian, Yi Fang
· 0 citations