Agent-written tests made repair worse.

ExecCritic separates test construction from repair so the same trajectory never writes both the patch and the test judging it, with a fail-closed harness qualifying and freezing tests before the Repair agent sees them. Holding the Repair agent fixed on SWE-bench Verified, tests from the untrained Test agent cut resolved rate from a 61.2% no-test baseline to 57.3%, while tests from a stronger model raised it to 65.3%. Role-specific post-training took the Test agent's Base-to-Gold success from 22.2% to 62.2% and the composed pair reached 72.6%. arXiv 2609.09133