类型化决策模型何时适用于交通问题?出行选择与交通信号控制的实证研究
When Do Typed Decision Models Work in Transportation? Evidence from Travel Choice and Traffic Signal Control
AI 导读
一项 arXiv 研究评估类型化决策模型在两类交通任务中的表现。在 Swissmetro 数据集上,TypeSafe Jev 和 GPT-6 Luna Decisions 的出行方式预测准确率低于传统离散选择模型和最强的对话式基线,且表现随输入表示变化明显;在闭环交通信号控制中,它们在部分场景具有竞争力,但复杂网络条件下性能下降。
正文 · 原文
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.AI · arxiv.org