1
When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation
68-cell测量实验揭示LLM代理区分表面噪声与语义噪声的边界,对理解模型鲁棒性有重要意义。
arXiv:2605.25981v1 Announce Type: new Abstract: We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language …