ExecCritic separates test-writing from repair and trains both with RL

ExecCritic (arXiv 2609.09133, Wed 9 Sep digest) addresses the false-confidence failure of coding agents whose tests and patches are written by the same trajectory — the errors agree, so execution feedback looks green while behavior is wrong. Its test-verify-revise scaffold separates the roles: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code against their execution feedback without touching the tests. Both roles use Qwen-3.5-35B-A3B as backbone and are trained separately with role-specific RL; on Learn-to-Test and execution-feedback benchmarks the scaffold outperforms single-trajectory agents.

The same-trajectory test-and-patch failure mode is well known to anyone running agentic CI. Teams can adopt the scaffold pattern without the RL: routing test generation and repair through different contexts already removes the correlated-error failure, and the fail-closed freeze is a one-line policy.