@article{canwetrustablackboxllmllmuntrustworthybo, title = {Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning}, author = {Xiaotian Zhou and Di Tang and Xiaofeng Wang and Xiaozhong Liu}, year = {2026}, eprint = {2604.05483}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.05483}, }