The Central Coupler of the AAA+ ATPase ClpXP Controls Intersubunit Communication and Couples the Conversion of Chemical Energy into the Generation of Force

ClpX is a clockwise hexameric helical arrangement that hydrolyzes ATP to unfold proteins and translocate them into the proteolytic chamber. We investigate the central coupler,

Structural features of E. coli Stx bacteriophage phi24B revealed with cryo-electron microscopy

Shiga toxin-converting bacteriophages play a critical role in the emergence and virulence of pathogenic Escherichia coli strains. Despite their significance, detailed structural information on these

Optimization of AAV tools to target M&uumlller glial cells for retinal gene therapy

Reprogramming of M&uumlller glial (MG) cells into retinal neurons has the potential to treat vision loss by regenerating the retina. Development of efficient gene delivery

scMultiPreDICT: A single-cell predictive framework with transcriptomic and epigenetic signatures

Cellular responses to genetic perturbations depend on both transcriptional programs and the epigenetic landscape. While single-cell multiomics technologies enable simultaneous profiling of gene expression and

Engineering a Glucose-Inducible Whole-Cell Biosensor via CRISPRi-Based Promoter Reprogramming

Precise monitoring of intracellular glucose dynamics is essential for understanding carbon flux, optimizing microbial bioprocesses, and enabling responsive control of engineered metabolic pathways. Here, we

Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects

April 9, 2026

arXiv:2604.06373v1 Announce Type: cross
Abstract: New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project. These AI IDEs are increasingly perceived as capable of producing project-level code at scale. However, there is limited empirical evidence on the extent to which they can generate large-scale software systems and what design issues such systems may exhibit. To address this gap, we conducted a study to explore the capability of Cursor in generating large-scale projects and to evaluate the design quality of projects generated by Cursor. First, we propose a Feature-Driven Human-In-The-Loop (FD-HITL) framework that systematically guides project generation from curated project descriptions. We generated 10 projects using Cursor with the FD-HITL framework across three application domains and multiple technologies. We assessed the functional correctness of these projects through manual evaluation, obtaining an average functional correctness score of 91%. Next, we analyzed the generated projects using two static analysis tools, CodeScene and SonarQube, to detect design issues. We identified 1,305 design issues categorized into 9 categories by CodeScene and 3,193 issues in 11 categories by SonarQube. Our findings show that (1) when used with the FD-HITL framework, Cursor can generate functional large-scale projects averaging 16,965 LoC and 114 files; (2) the generated projects nevertheless contain design issues that may pose long-term maintainability and evolvability risks, requiring careful review by experienced developers; (3) the most prevalent issues include Code Duplication, high Code Complexity, Large Methods, Framework Best-Practice Violations, Exception-Handling Issues and Accessibility Issues; (4) these design issues violate design principles such as SRP, SoC, and DRY. The replication package is at https://github.com/Kashifraz/DIinAGP

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd. dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registration number 16808844