Generation of Web Apps with Agentic IDEs: An Empirical Assessment
Source
arxiv.org
Author
Manuel Marceca, Maria Teresa Rossi, Leonardo Mariani
Date
Why it matters
Agentic IDEs handle established patterns like CRUD and auth reliably but produce significantly more errors on less common distributed architectures such as task queues — scope what you hand an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → accordingly.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
articleFramework and Benchmark for Code-Driven Agentic Testing in Web DevelopmentBin Hong, Zhenchao Zhang, Jiyuan He, Kai Zhang, Zhenya Huang
articleHxAgent: Iterative Agent Planning for End-to-End Web Application TestingTu Nguyen, Duy Cao, Viet Nguyen, Phu Nguyen, Vy Le, Nguyen TK Nguyen, Tien N. Nguyen, Vu Nguyen
articleA Study of the Reliability of Agentic AI-Generated ProgramsAyesha Shafique, Barton P. MIller, Elisa R. Heymann