1
Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
A*算法驱动多智能体，对LLM提示发起常识混淆攻击，揭示大模型语言理解的脆弱性。
arXiv:2606.01441v1 Announce Type: new Abstract: Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to…