Reproduce “Traffic Performance GPT (TP-GPT): Real-Time Data Informed Intelligent ChatBot for Transportation Surveillance and Management” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Bingzhang Wang, Zhiyu Cai, Muhammad Monjurul Karim, Chenxi Liu, Yinhai Wang
TP-GPT turns plain-language traffic questions into SQL queries, checks and runs them, then explains returned data. Its four-agent workflow uses specialized prompts, retrieved examples, and iterative checking to generate, revise, and interpret queries. On 50 manually designed TransQuery tasks, TP-GPT produced 40 flawless answers (80%) and averaged 0.87, versus GPT-4 Turbo’s 22 flawless answers (44%) and 0.57; results are limited to this test set.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.