Function-Level Execution Feedback for Code Preference Optimization

arXiv cs.AIAugust 26, 2026en

arXiv:2608.23632v1 Announce Type: new Abstract: Process supervision has improved mathematical reasoning, where intermediate steps are naturally expressed as chains of thought. In code generation, however, process supervision remains underexplored because there is no standard notion of a step. Supervision can target lines, reasoning traces, or program states, making it unclear what to label and optimize. We propose STEP-KTODER, a framework for code preference optimization that defines steps as module-level functions in decomposed multi-function programs and assigns binary correctness labels via automatically generated unit tests. Our method provides a code-specific instantiation of stepwise K

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning