Agent-generated code produces up to 13.1% lower follow-on task resolution rates than human code in chained repository-level experiments, with differences linked to behavioral patterns rather than conventional metrics.
An empirical study on bug severity estimation using source code metrics and static analysis
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Correlative tomography and mass-balance analysis show that grain morphology governs decomposition and pore evolution during oxidation of Cr2AlC coatings.
citing papers explorer
-
Is Agent Code Less Maintainable Than Human Code?
Agent-generated code produces up to 13.1% lower follow-on task resolution rates than human code in chained repository-level experiments, with differences linked to behavioral patterns rather than conventional metrics.