arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.03363cs.LG
收藏

面向交通智能体AI应用的多标签意图识别的模块化、无数据流水线

A Modular, Data-Free Pipeline for Multi-Label Intention Recognition in Transportation Agentic AI Applications

Department of Infrastructure Engineering, Faculty of Engineering and Information Technology, The University of Melbourne, Australia（工程与信息技术学院基础设施工程系，墨尔本大学，澳大利亚）；School of Computing, National University of Singapore, Singapore（计算学院，新加坡国立大学，新加坡）；Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore（高性能计算研究所，科学、技术与研究局（A*STAR），新加坡）；Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR（土木与环境工程系，香港科学与技术大学，香港特别行政区）

Xiaocai Zhang, Hur Lim, Ke Wang, Zhe Xiao, Jing Wang, Kelvin Lee, Xiuju Fu, Zheng Qin

备注：
Present in the Transportation Research Board (TRB) Annual Meeting 2026
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出模块化无数据流水线DMTC，通过LLM合成查询、Sentence-T5嵌入和在线焦点对比损失训练轻量分类器，实现交通智能体AI中的多标签意图识别，并在海事场景中取得优于现有方法的性能。

摘要：

本研究提出了一种模块化、无数据的多标签意图识别流水线，用于交通领域的智能体AI应用。传统的意图识别系统依赖大规模标注语料，且往往难以实现细粒度、多标签的判别，而我们的方法消除了昂贵的数据采集需求，同时提升了多标签意图理解的准确性。具体而言，该整体流水线命名为DMTC，包含三个步骤：1）利用提示工程引导大语言模型（LLMs）生成不同交通场景下的多样化合成查询；2）使用Sentence-T5模型对每个文本查询进行编码，以获得紧凑的语义嵌入；3）使用一种新颖的在线焦点对比（OFC）损失训练轻量级分类器，该损失强调困难样本并最大化类间可分性。该流水线的适用性在海事运输背景下的智能体AI应用中得到了验证。大量实验表明，DMTC实现了5.35%的汉明损失和95.92%的AUC，优于最先进的多标签分类器以及近期端到端SOTA的基于LLM的基线方法。进一步分析表明，与其他编码器相比，Sentence-T5嵌入将子集准确率提高了至少3.29%，并且与标准对比目标相比，引入OFC损失额外带来了0.98%的提升。总之，我们的系统能够将用户查询无缝路由到任务特定模块（例如ETA信息、交通风险评估以及交通领域的其他典型场景），为无需昂贵人工标注的完全自主、意图感知的智能体奠定了基础。

英文摘要：

In this study, a modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation. Unlike traditional intent recognition systems that depend on large, annotated corpora and often struggle with fine-grained, multi-label discrimination, our approach eliminates the need for costly data collection while enhancing the accuracy of multi-label intention understanding. Specifically, the overall pipeline, named DMTC, consists of three steps: 1) using prompt engineering to guide large language models (LLMs) to generate diverse synthetic queries in different transport scenarios; 2) encoding each textual query with a Sentence-T5 model to obtain compact semantic embeddings; 3) training a lightweight classifier using a novel online focal-contrastive (OFC) loss that emphasizes hard samples and maximizes inter-class separability. The applicability of the proposed pipeline is demonstrated in an agentic AI application in the maritime transportation context. Extensive experiments show that DMTC achieves a Hamming loss of 5.35% and an AUC of 95.92%, outperforming state-of-the-art multi-label classifiers and recent end-to-end SOTA LLM-based baselines. Further analysis reveals that Sentence-T5 embeddings improve subset accuracy by at least 3.29% over alternative encoders, and integrating the OFC loss yields an additional 0.98% gain compared to standard contrastive objectives. In conclusion, our system seamlessly routes user queries to task-specific modules (e.g., ETA information, traffic risk evaluation, and other typical scenarios in the transportation domain), laying the groundwork for fully autonomous, intention-aware agents without costly manual labelling.

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。

↑