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

TL;DR

This paper introduces a modular, data-free pipeline for multi-label intention recognition in transportation AI, using synthetic data generation, semantic embeddings, and a novel loss to improve accuracy without manual labeling.

Contribution

The proposed DMTC pipeline eliminates the need for annotated data and enhances multi-label intention recognition accuracy in transportation AI applications.

Findings

Achieves a Hamming loss of 5.35% and an AUC of 95.92%.

Outperforms state-of-the-art classifiers and recent LLM baselines.

Sentence-T5 embeddings improve subset accuracy by at least 3.29%.

Abstract

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.