Code Models · 2022

Execution Feedback / Unit-Test Gen / Program Repair

Bei Chen, Jian-Guang Lou, Weizhu Chen, Xinyun Chen, Denny Zhou

This line closed the loop between generation and correctness by using program execution and unit tests as a feedback signal, so models could generate tests, run candidate code, read the errors, and repair themselves instead of relying on the first output.

Editorial record

Plain-language summary

Rather than treating a generated program as final, these methods execute it against unit tests (often model-generated) and feed the resulting pass/fail signals and error traces back to guide selection or iterative repair. Approaches include ranking candidates by test agreement, self-debugging from stack traces, and generating tests to expose faults. This grounds code models in an objective oracle, letting them fix functional bugs that pure next-token likelihood cannot detect.

Knowledge graph

Relationships

Descendants

Source record

Provenance

Record ID
P-344
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.