Licheng Wang

The paper introduces extsc{Spore}, a novel, training-free, and highly efficient privacy extraction attack that targets sensitive information stored in the memory of LLM agents during inference, outperforming existing state-of-the-art methods.

This paper surveys 1,250 arXiv papers on self-improving AI systems, categorizing them based on what they improve and the degree of loop closure. It identifies a distinctive feature of self-evaluation and explores the evaluator design space.