2 papers
cs.AI2025
Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model
Yanhao Li, Lu Ma, Jiaran Zhang +3
Existing approaches typically rely on fixed length penalties, but such penalties are hard to tune and fail to adapt to the evolving reasoning abilities of LLMs, leading to suboptim…
cs.SE2025
Attention Distance: A Novel Metric for Directed Fuzzing with Large Language Models
Wang Bin, Ao Yang, Kedan Li +5
In the domain of software security testing, Directed Grey-Box Fuzzing (DGF) has garnered widespread attention for its efficient target localization and excellent detection performa…