通信学报2026，Vol.47Issue(2)：125-139,15.DOI:10.11959/j.issn.1000-436x.2026033
模型互联网中基于自我效能的Token级多模型协作
Token-level multi-model collaboration based on self-efficacy in AI-model network
摘要
Abstract
To address the trade-off between inference performance and cost in Token-level collaboration within the AI-model network,a self-efficacy-based Token-level multi-model collaboration method named ConfiPara was proposed.Firstly,a Token-level collaborative method with an exit mechanism was designed to mitigate the high overhead of exis-ting approaches.Secondly,a self-efficacy assessment algorithm integrating the base model's confidence and reliability was introduced to determine the optimal exit timing.By leveraging self-efficacy to guide the base model in switching to independent inference at appropriate moments,redundant collaboration was skipped,thereby maintaining accuracy while reducing Token overhead.Experimental results demonstrate that the proposed ConfiPara method achieves a substantial reduction in Token consumption and inference latency with only a minor accuracy loss.In a single collaborative model scenario,the method reduces Token cost by approximately 21%and cuts per-Token generation latency by up to 75%,at the cost of only a 2.5%drop in accuracy.关键词
大模型/模型互联网/Token级模型协作/退出机制/自我效能Key words
large model/AI-model network/Token-level model collaboration/exit mechanism/self-efficacy分类
信息技术与安全科学引用本文复制引用
王建辉,李哲涛,石伟凡,王泽平,郑智润,李成新..模型互联网中基于自我效能的Token级多模型协作[J].通信学报,2026,47(2):125-139,15.基金项目
国家自然科学基金资助项目(No.W2411053,No.U23B2027) The National Natural Science Foundation of China(No.W2411053,No.U23B2027) （No.W2411053,No.U23B2027）
