arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.18550cs.NI
收藏

JAUNT:面向以QoE为中心的LLM工具路由的用户意图与网络状态联合对齐

JAUNT: Joint Alignment of User Intent and Network State for QoE-centric LLM Tool Routing

The University of Hong Kong(香港大学)

Enhan Li, Hongyang Du

AI总结:

针对LLM工具路由仅做语义功能匹配、忽视用户意图模糊性及网络状态影响QoE的问题,提出JAUNT双视图对齐框架与配套基准,实验证明其显著优于基线。

摘要:

大语言模型(LLM)越来越依赖模型上下文协议(MCP)等新兴协议来调用外部工具和服务。然而,当前的工具路由机制仍然脆弱,因为它们只考虑用户查询与工具之间的功能匹配。在实践中,通过查询表达的用户意图可能模糊或不明确,而实际体验质量(QoE)还取决于链路延迟和服务器可用性等外部因素,这些因素无法仅通过语义捕获。为应对这一挑战,我们提出JAUNT,这是一个在以QoE为中心的工具路由中联合对齐用户意图和网络状态的框架。JAUNT引入双视图对齐策略,在解释用户意图的同时,利用LLM智能体构建网络画像,将数值性能指标映射到语义空间以指导路由。我们进一步设计了一个基准,将多样化的用户请求模式与异构网络状态相结合,从而能够系统评估QoE结果。实验结果表明,与若干基线相比,JAUNT显著提升了QoE,证明了同时对齐意图和网络状态对于可扩展的LLM服务编排的重要性。

英文摘要:

Large Language Models (LLMs) increasingly rely on emerging protocols such as the Model Context Protocol (MCP) to invoke external tools and services. However, current tool routing mechanisms remain fragile because they only consider functional matching between users' queries and tools. In practice, user intent expressed through queries can be vague or underspecified, and the actual Quality of Experience (QoE) also depends on external factors such as link latency and server availability that are not captured by semantics alone. To address this challenge, we propose JAUNT, a framework for Joint Alignment of User intent and Network state in QoE-centric Tool routing. JAUNT introduces a dual-view alignment strategy that interprets user intent while employing LLM agents to construct network profiles, mapping numerical performance indicators into the semantic space to guide routing. We further design a benchmark that integrates diverse user request patterns with heterogeneous network states, enabling systematic evaluation of QoE outcomes. Experimental results show that JAUNT significantly improves QoE compared with several baselines, demonstrating the importance of aligning both intent and network state for scalable LLM service orchestration.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑