基于记忆增强型智能体的人工智能信任语义蒸馏用于合作者选择
人工智能
2025-12-24 v2
摘要
将计算任务从资源受限的设备卸载到资源丰富的对等设备构成了协作计算中的关键范式。在此背景下,对潜在合作设备进行准确的信任评估对于有效执行复杂计算任务至关重要。这种信任评估过程涉及从每个潜在合作者那里收集多样化的信任相关信息,并基于收集的数据进行信任推断。然而,当每个资源受限的设备独立评估所有潜在合作者时,频繁的数据交换和复杂的推理会造成显著的开销,并进一步降低信任评估的及时性。为克服这些挑战,我们提出了一种基于大型人工智能模型 (LAM) 启发的教师-学生智能体架构的任务特定信任语义蒸馏 (TSD) 模型。具体而言,教师智能体部署在具有强大计算能力的服务器上,并增配记忆模块,用于多维信任相关数据收集、任务特定信任语义提取和任务-合作者匹配分析。Upon receiving task-specific evaluation requests from device-side student agents, the teacher agent transfers the trust semantics of potential collaborators to the student agents, enabling rapid and accurate collaborator selection. Experimental results demonstrate that the proposed TSD model can reduce collaborator evaluation time, decrease device resource consumption, and improve the accuracy of collaborator selection.
引用
@article{arxiv.2509.08151,
title = {Trust Semantics Distillation for Collaborator Selection via Memory-Augmented Agentic AI},
author = {Botao Zhu and Jeslyn Wang and Dusit Niyato and Xianbin Wang},
journal= {arXiv preprint arXiv:2509.08151},
year = {2025}
}