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 Validation of Cognitive Complexity as a Measure of Source Code Understandability , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.