3 papers
cs.CL2026
RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience
Yang Wu, Junran Pan, Yifan Zhang +3
Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods hav…
cs.CL2025
Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs
Yang Wu, Yifan Zhang, Yiwei Wang +5
While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, growing evidence suggests much of their success stems from memorized answer-reasoning patterns rat…
cs.CL2025
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
Yurong Wu, Fangwen Mu, Qiuhong Zhang +8
Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates th…