Harnessing LLMs for Document-Guided Fuzzing of Python Libraries
Source
Bin Duan, Tarek Mahmud, Meiru Che, Yan Yan, Naipeng Dong, Dan Dongseong Kim, Guowei Yang
Author
Bin Duan, Tarek Mahmud, Meiru Che, Yan Yan, Naipeng Dong, Dan Dongseong Kim, Guowei Yang
Published
Why it matters
Shows a local model reading docs well enough to drive fuzzing at scale, and quantifies how much of an API surface has cross-parameter constraints that naive generators break on.
articleLost in Compaction: Evaluating Side-Constraint Loss under Context CompactionZhiqi Wang, Yichi Zhang, Dongwon Lee, Yuchen Yang
articleThe Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent BehaviorXiangzhe Xu, Hamidreza Saghir, Qianhui Wu, Marc-Alexandre C\^ot\'e, Tong Wang, Kiran Lakkaraju, Kexin Pei, Xiangyu Zhang
articleHow well LLM-based test generation techniques perform with newer LLM versions?Michael Konstantinou, Renzo Degiovanni, Mike Papadakis