2 papers
cs.CR2026
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Zihan Zhang, Shuangjie Yao, Zesen Liu +8
Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similarity betwee…
cs.AI2026
Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring
Zhixiang Zhang, Zesen Liu, Wai Ip Lai +2
Self-evolving agent harnesses continually update persistent components such as memory, prompts, skills, and tools. We call this process harness evolution. However, such evolution c…