2 papers
cs.AI2026
From Errors to Rules: Iterative Prompt Optimization for Text Classification
Yueying Cui, Renhao Xue, Yi Zhang +1
Prompt optimization for text classification spans diverse approaches, from demonstration selection to exploration-based search to error-driven diagnosis, each with known but incomp…
cs.CR2026
MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
Jifeng Gao, Kang Xia, Yi Zhang +5
Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, reta…