Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning 事件

Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning arXiv:2605.28305v1 Announce Type: new Abstract: Large Language Models (LLMs) often produce explicit reflective traces during complex reasoning, accompanied by anthropomorphic markers such as wait, hmm, and alternatively. Although these markers are commonly used as visible indicators of reflection, their mechanisms remain unclear, which leaves the risk of overthinking associated with redundant and repetitive reflecti