Automating Traffic Model Enhancement with AI Research Agent
arXiv:2409.16876 · doi:10.1016/j.trc.2025.105187
Abstract
Developing efficient traffic models is crucial for optimizing modern transportation systems. However, current modeling approaches remain labor-intensive and prone to human errors due to their dependence on manual workflows. These processes typically involve extensive literature reviews, formula tuning, and iterative testing, which often lead to inefficiencies. To address this, we propose TR-Agent, an AI-powered framework that autonomously develops and refines traffic models through a closed-loop, iterative process. We structure the research pipeline into four key stages: idea generation, theory formulation, theory evaluation, and iterative optimization, and implement TR-Agent with four corresponding modules. These modules collaborate to retrieve knowledge from external sources, generate novel hypotheses, implement and debug models, and evaluate their performance on evaluation datasets. Through iteratively feedback and refinement, TR-Agent improves both modeling efficiency and effectiveness. We validate the framework on three representative traffic models: the Intelligent Driver Model (IDM) for car-following behavior, the MOBIL model for lane-changing, and the Lighthill-Whitham-Richards (LWR) speed-density relationship for macroscopic traffic flow modeling. Experimental results show substantial performance gains over the original models. To assess the robustness and generalizability of the improvements, we conduct additional evaluations across multiple real-world datasets, demonstrating consistent performance gains beyond the original development data. Furthermore, TR-Agent produces interpretable explanations for each improvement, enabling researchers to easily verify and extend its results. This makes TR-Agent a valuable assistant for traffic modeling refinement and a promising tool for broader applications in transportation research.
27 pages, 12 figures
References in corpus (24)
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- LLaMA: Open and Efficient Foundation Language Models
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
- A Survey of Large Language Models
- Evaluating Large Language Models Trained on Code
- ReAct: Synergizing Reasoning and Acting in Language Models
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Reflexion: Language Agents with Verbal Reinforcement Learning
- ChemCrow: Augmenting large-language models with chemistry tools
- FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modeling
- SciMON: Scientific Inspiration Machines Optimized for Novelty
- Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers
- EvoPrompting: Language Models for Code-Level Neural Architecture Search
- ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models
- An LLM Agent for Automatic Geospatial Data Analysis
- Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
- Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering
- DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
- Large Language Models are Zero Shot Hypothesis Proposers
- OMNI: Open-endedness via Models of human Notions of Interestingness
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
- Discovering Preference Optimization Algorithms with and for Large Language Models
- GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databases