TestEvo-Bench supplies 746 test-generation and 509 test-update tasks from 152 Java repositories, each tied to actual commits and packaged for execution-based scoring, with current agents reaching 77.5% and 74.6% success respectively.
Brett Daniel, Vilas Jagannath, Danny Dig, and Darko Marinov
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
-
TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
TestEvo-Bench supplies 746 test-generation and 509 test-update tasks from 152 Java repositories, each tied to actual commits and packaged for execution-based scoring, with current agents reaching 77.5% and 74.6% success respectively.