Customized Generative AI Agent for Transportation Engineering Practice: A Development and Continued Pre-training Guideline
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
Recent advancements in generative artificial intelligence (AI) and large language models (LLMs) have shown significant promise in automating complex reasoning, summarization, and question-answering tasks. However, the effectiveness of general-purpose LLMs in specialized engineering domains remains limited due to insufficient exposure to technical standards, engineering terminology, and domain-specific semantics. This study proposes a systematic approach to developing a customized generative AI agent for transportation engineering applications. A curated corpus of U.S. transportation manuals, design guidelines, and regulatory documents is used to conduct continued pretraining of six state-of-the-art LLMs through a unified low-rank adaptation (LoRA) framework. The training process is monitored to ensure convergence and model stability. Performance is evaluated using standard natural language processing metrics, including BLEU-4 and ROUGE, with Qwen2.5-7B and LLaMA-3.1-8B demonstrating the highest domain alignment and response quality. Results validate the effectiveness of LoRA-based adaptation in improving LLM performance on technical content interpretation and context-specific reasoning. This work contributes a reproducible development framework for constructing domain-specialized generative AI agents, supporting broader deployment in transportation research, design, planning, and policy analysis.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 22 of its 52 references that are in the map. First posted on arXiv 27 Jun 2026.
Builds on
22 of 52 references.
References · 22
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2020Measuring Massive Multitask Language Understandingcited by 7,768
- 2024Qwen2.5 Technical Reportcited by 4,713
- 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
- 2024A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendationscited by 84
- 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
- 2023TrafficSafetyGPT: Tuning a Pre-trained Large Language Model to a Domain-Specific Expert in Transportation Safetycited by 27
- 2024TSpec-LLM: An Open-source Dataset for LLM Understanding of 3GPP Specificationscited by 26
- 2024Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysiscited by 20
- 2023PolicyGPT: Automated Analysis of Privacy Policies with Large Language Modelscited by 16
- 2024Using Large Language Models to Understand Telecom Standardscited by 13
- 2024Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networkscited by 8
10 more
- 2024Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standardscited by 8
- 2024Digital Network Twins for Next-generation Wireless: Creation, Optimization, and Challengescited by 8
- 2025INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluationcited by 5
- 2023Using Collision Momentum in Deep Reinforcement Learning Based Adversarial Pedestrian Modelingcited by 4
- 2024Deep Reinforcement Learning for Advanced Longitudinal Control and Collision Avoidance in High-Risk Driving Scenarioscited by 4
- 2024Large Language Model in Financial Regulatory Interpretationcited by 3
- 2024Enhancing Travel Choice Modeling with Large Language Models: A Prompt-Learning Approachcited by 3
- 2025Synergizing AI and Digital Twins for Next-Generation Network Optimization, Forecasting, and Securitycited by 3
- 2024Risks and NLP Design: A Case Study on Procedural Document QAcited by 2
- 2023Multiclass Classification of Policy Documents with Large Language Modelscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Benchmarking the Capabilities of Large Language Models in Transportation System Engineering: Accuracy, Consistency, and Reasoning Behaviors
- 2025LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis
- 2025Evaluating Retrieval Augmented Generative Models for Document Queries in Transportation Safety
- 2025Generative AI in Transportation Planning: A Survey
- 2024GenAI-powered Multi-Agent Paradigm for Smart Urban Mobility: Opportunities and Challenges for Integrating Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) with Intelligent Transportation Systems
- 2024Creating an LLM-based AI-agent: A high-level methodology towards enhancing LLMs with APIs
- 2025Towards more Contextual Agents: An extractor-Generator Optimization Framework
- 2024Beyond Words: Evaluating Large Language Models in Transportation Planning