# Automating Traffic Model Enhancement with AI Research Agent

arXiv: https://arxiv.org/abs/2409.16876 · HTML: https://mlsanity.com/paper/2409.16876/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 76 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 30)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers](https://mlsanity.com/paper/2212.10559/) (2022)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [EvoPrompting: Language Models for Code-Level Neural Architecture Search](https://mlsanity.com/paper/2302.14838/) (2023)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [AutoML-GPT: Automatic Machine Learning with GPT](https://mlsanity.com/paper/2305.02499/) (2023)
- [OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code](https://mlsanity.com/paper/2405.15568/) (2024)
- [OMNI: Open-endedness via Models of human Notions of Interestingness](https://mlsanity.com/paper/2306.01711/) (2023)
- [Large Language Models As Evolution Strategies](https://mlsanity.com/paper/2402.18381/) (2024)
- [Dissipation of stop-and-go waves via control of autonomous vehicles: Field experiments](https://mlsanity.com/paper/1705.01693/) (2017)
- [Large Language Models are Zero Shot Hypothesis Proposers](https://mlsanity.com/paper/2311.05965/) (2023)
- [Discovering Preference Optimization Algorithms with and for Large Language Models](https://mlsanity.com/paper/2406.08414/) (2024)
- [Data-driven Traffic Simulation: A Comprehensive Review](https://mlsanity.com/paper/2310.15975/) (2023)
- [FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modeling](https://mlsanity.com/paper/2306.05381/) (2023)
- [PCNN: Deep Convolutional Networks for Short-term Traffic Congestion Prediction](https://mlsanity.com/paper/2003.07033/) (2020)
- [Modeling car-following behavior on urban expressways in Shanghai: A naturalistic driving study](https://mlsanity.com/paper/1811.06395/) (2018)
- [A Hybrid Rule-Based and Data-Driven Approach to Driver Modeling through Particle Filtering](https://mlsanity.com/paper/2108.12820/) (2021)

## Built on by (most cited first, 8 of 8)

- [LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarios](https://mlsanity.com/paper/2505.11247/) (2025)
- [AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing](https://mlsanity.com/paper/2510.19661/) (2025)
- [Aligning LLM agents with human learning and adjustment behavior: a dual agent approach](https://mlsanity.com/paper/2511.00993/) (2025)
- [Agentic Vehicles for Human-Centered Mobility: Definition, Prospects, and Synergistic Co-Development with Vehicle Autonomy](https://mlsanity.com/paper/2507.04996/) (2025)
- [LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs](https://mlsanity.com/paper/2510.22333/) (2025)
- [EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions](https://mlsanity.com/paper/2605.02289/) (2026)
- [Advanced Assistance for Traffic Crash Analysis: An AI-Driven Multi-Agent Approach to Pre-Crash Reconstruction](https://mlsanity.com/paper/2511.10853/) (2025)
- [Large Multimodal Agents for Intelligent Transportation Systems: Architectures, Evidence, and Deployment Challenges](https://mlsanity.com/paper/2608.08184/) (2026)

## Abstract (arXiv)

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.