多智能体系统终于有了统一的置信度评估方法，做NLP系统可靠性或智能体协作的团队可以直接参考协议设计，提升系统可信度。
现有自然语言处理（NLP）方法中，置信度用于可靠性、监督和下游决策，但尚无方法为多智能体系统的输出生成或评估置信度。本文提出三种协议，通过将原始置信度信号跨模型可比化，再经软投票或贝叶斯融合聚合，输出最终答案及单一聚合置信度。实验表明，聚合置信度的判别能力（AUARC）显著优于最佳单智能体或标准辩论基线，而正确性（F1分数）保持稳定，并恢复了多智能体辩论在模糊任务上的损失。研究分析了序列概率和自报告两种估计器，以及参数与非参数校准器，发现校准可提升F1，而AUARC对校准依赖较小。在五个基准和四种任务类型上，评估了六组同质和异质辩论对，覆盖不同模型能力和规模。
Multiagent Protocols with Aggregated Confidence Signals
Confidence is used for reliability, oversight, and a range of downstream decision tasks in Natural Language Processing (NLP), yet no existing method produces or evaluates a confidence for the output of a multiagent system. Prior work uses confidence within multiagent debate (MAD) to weight messages, trigger debate, or calibrate individual agents, but it never aggregates these into a single confidence for the system itself. We introduce three protocols that produce a final answer along with a single aggregated confidence by first transforming raw confidence signals to make them comparable across models, then combining them via soft voting or a probability fusion we call Bayesian fusion. This aggregated confidence is substantially more discriminative (AUARC) than that of the best single agent or the standard debate baselines, while correctness (F1-score) stays stable and recovers the losses MAD incurs on more ambiguous tasks. Analyzing two estimators, sequence probability and self-report, alongside parametric and non-parametric calibrators, we find that calibration improves F1 for both estimators while AUARC is less reliant on it. We evaluate six homogeneous and heterogeneous debating pairs per benchmark, across five benchmarks and four task types, spanning a range of model capabilities and sizes.