Code Models · 2022
Execution Feedback / Unit-Test Gen / Program Repair
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
EnablesEvidence: Direct
Open Code Models (StarCoder/Code Llama/DeepSeek-Coder/Qwen-Coder)
Open code models enable execution-feedback loops
P-344
Source record
Provenance
- Record ID
- P-344
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2207.10397
- arXiv:2207.10397
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.