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

2026-01-21

AI Summary

This work addresses the limitations of existing single-agent large language models, which often exhibit bias when processing heterogeneous traffic accident data and struggle to meet the high accuracy and stability demands of emergency response systems. To overcome this, we propose the first hybrid multi-agent framework specifically designed for predicting traffic accident severity. The framework employs specialized agents to handle distinct subtasks—such as demographic factors, environmental context, and accident details—and integrates their intermediate outputs via a multilayer perceptron, enabling decoupled domain knowledge representation and collaborative reasoning. Compatible with various backbone models including GPT-3.5, GPT-4o, and LLaMA-3.3, the approach significantly outperforms conventional machine learning and single-agent methods on both CPSRMS and NEISS datasets, demonstrating superior robustness, interpretability, and cross-dataset generalization capability.

Technology Category

• Multiagent Systems: Adversarial Agents
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• traffic accident severity prediction
• large language models
• heterogeneous data
• prediction bias
• single-agent limitations

Innovation

• multi-agent LLM
• traffic accident severity prediction
• heterogeneous data integration
• MLP fusion module
• calibrated prediction