CoSPlay jointly refines self-generated codes and unit tests via bidirectional pass-count signals and consensus selection, raising pass@N and UT accuracy on code benchmarks without ground-truth data.
Revisit self-debugging with self-generated tests for code generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
CoSPlay jointly refines self-generated codes and unit tests via bidirectional pass-count signals and consensus selection, raising pass@N and UT accuracy on code benchmarks without ground-truth data.