1
Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate
基于早期token置信度，预测多智能体LLM辩论的推理质量，为高效协调提供新思路。
arXiv:2606.10307v1 Announce Type: new Abstract: Evaluating reasoning quality in multi-agent LLM systems is challenging, especially for open-ended task…