跳到正文
arXiv cs.CL· Hongyang Zhang, Boyuan Deng, Siyuan Feng, Kai Chen, Junbo Zhang·· 23 小时前AI 评分31

类型化决策模型何时适用于交通领域?来自出行选择与交通信号控制的证据

When Do Typed Decision Models Work in Transportation? Evidence from Travel Choice and Traffic Signal Control

AI 导读

研究在出行方式选择预测与交通信号控制两类任务中评估了 TypeSafe Jev 和 GPT-6 Luna Decisions 等类型化决策模型。在 Swissmetro 数据集上,其预测准确率低于传统离散选择模型和最强聊天式基线,且表现随输入表示与提问方式大幅波动;闭环信号控制中部分场景具竞争力,但更复杂路网下性能下降。其推理延迟与计算成本低于所评估的聊天式大语言模型。

正文 · 原文

View PDF

Abstract:Typed decision models combine natural-language understanding with a structured interface that returns a selected action and an option-level probability distribution without generating lengthy textual responses. Their low inference cost and response latency make them attractive for transportation problems with predefined alternatives. This paper investigates their effectiveness, robustness, and efficiency in two representative transportation tasks: individual travel-mode choice prediction and sequential traffic signal control. We systematically evaluate TypeSafe Jev and GPT-6 Luna Decisions against conventional transportation methods, reinforcement learning algorithms, and four chat-based large language models. Experiments on the Swissmetro dataset show that typed decision models achieve lower prediction accuracy than traditional discrete choice models and the strongest chat-based baseline, while their performance varies substantially with input representation and question framing. In closed-loop traffic signal control experiments, typed decision models demonstrate competitive performance against established controllers in several scenarios, but exhibit performance degradation under more challenging network conditions. Furthermore, the typed models achieve lower inference latency and computational cost than the evaluated chat-based large language models, highlighting their potential for efficient, zero-shot transportation decision-making. Overall, these findings demonstrate both the potential and limitations of typed decision models, emphasizing the importance of input design, task characteristics, and robustness evaluation for their effective application in transportation systems.
Comments: 22 pages, 4 figures
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
MSC classes: 68T50 (Primary) 90B20, 91B06 (Secondary)
ACM classes: I.2.7; I.2.8; J.2
Cite as: arXiv:2611.22926 [cs.CL]
  (or arXiv:2611.22926v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.22926

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Boyuan Deng [view email]
[v1] Tue, 17 Nov 2026 15:24:40 UTC (951 KB)

来源:arXiv cs.CL · arxiv.org