arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.15519cs.AI
收藏

TransportAgents: 一种用于交通事故严重性预测的多智能体LLM框架

TransportAgents: a multi-agents LLM framework for traffic accident severity prediction

Civil and Environmental Engineering, University of Maryland(大学环境工程系,马里兰州大学);Computer and Information Science, University of Pennsylvania(计算机与信息科学系,宾夕法尼亚大学);Statistics, University of California, Berkeley(统计学系,加州大学伯克利分校)

Zhichao Yang, Jiashu He, Jinxuan Fan, Cirillo Cinzia

AI总结:

TransportAgents通过多智能体框架提升交通事故严重性预测的准确性与可靠性。

摘要:

准确预测交通事故严重性对于提高应急响应和公共安全规划至关重要。尽管最近的大型语言模型(LLMs)表现出强大的推理能力,但其单智能体架构往往难以处理异构、领域特定的事故数据,并且容易生成有偏见或不稳定预测。为了解决这些限制,本文提出了TransportAgents,一种混合多智能体框架,该框架整合了类别特定的LLM推理与多层感知机(MLP)整合模块。每个专门的智能体专注于特定的交通信息子集,如人口统计学、环境背景或事件细节,以生成中间严重性评估,随后融合到统一预测中。在两个互补的美国数据集,消费者产品安全风险管理系统(CPSRMS)和国家电子伤害监测系统(NEISS)上进行了广泛的实验,结果表明TransportAgents在传统机器学习和高级LLM基线方法上表现一致。在三种代表性骨干网络中,包括闭源模型如GPT-3.5和GPT-4o,以及开源模型如LLaMA-3.3,该框架表现出强大的鲁棒性、可扩展性和跨数据集泛化能力。补充的分布分析进一步显示,TransportAgents比标准单智能体LLM方法产生更平衡和校准的严重性预测,突显了其可解释性和可靠性,适用于安全关键决策支持应用。

英文摘要:

Accurate prediction of traffic crash severity is critical for improving emergency response and public safety planning. Although recent large language models (LLMs) exhibit strong reasoning capabilities, their single-agent architectures often struggle with heterogeneous, domain-specific crash data and tend to generate biased or unstable predictions. To address these limitations, this paper proposes TransportAgents, a hybrid multi-agent framework that integrates category-specific LLM reasoning with a multilayer perceptron (MLP) integration module. Each specialized agent focuses on a particular subset of traffic information, such as demographics, environmental context, or incident details, to produce intermediate severity assessments that are subsequently fused into a unified prediction. Extensive experiments on two complementary U.S. datasets, the Consumer Product Safety Risk Management System (CPSRMS) and the National Electronic Injury Surveillance System (NEISS), demonstrate that TransportAgents consistently outperforms both traditional machine learning and advanced LLM-based baselines. Across three representative backbones, including closed-source models such as GPT-3.5 and GPT-4o, as well as open-source models such as LLaMA-3.3, the framework exhibits strong robustness, scalability, and cross-dataset generalizability. A supplementary distributional analysis further shows that TransportAgents produces more balanced and well-calibrated severity predictions than standard single-agent LLM approaches, highlighting its interpretability and reliability for safety-critical decision support applications.

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。

↑