AI RESEARCH
FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework
arXiv CS.CL
•
ArXi:2605.02789v1 Announce Type: cross Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, which can reduce exploration efficiency and lead to redundant inputs. We present FunFuzz, a multi-island evolutionary fuzzing framework that runs several isolated searches in parallel and periodically migrates high-value candidates to maintain diversity.