Reassessing One-Round Test-Time Refinement for Code Generation

Abstract excerpt

Test-time refinement aims to improve generated programs through additional inference, but its value after an initial candidate has been produced remains unclear. We conduct a controlled evaluation of one-round Self-Refine and Self-Debug across seven models and three Python code-generation benchmarks. For each model and task, both methods refine the same initial candidate, allowing us to measure refinement gain wit...

Topics

Open a Topic to create a Post that cites this publication.

• Algorithms
• Computational Biology
• Drug Design
• Drug Discovery
• Phenotype

Identifiers and source

Literature Corpus work

c3c58019-9aa3-5447-b6f2-685a7cf69ae4

DOI

10.20944/preprints202608.0854.v1