ARTFEED — Contemporary Art Intelligence

Blind Resampling Outperforms Self-Repair in Small Code Models

other · 2026-07-30

A recent study published on arXiv (2607.26117) questions the conventional approach of self-repair in code generation models. Researchers utilized a placebo-controlled framework on MBPP+ across three model sizes (1.5B, 3B, 7B) to evaluate four retry scenarios: blind resampling, a content-free failure notice, authentic execution feedback, and feedback that included verbal self-reflection. The blind resampling method proved to be the most effective for models under 7B and was statistically equivalent at 7B, requiring 2.5-5.5 times fewer tokens. Conditioning on a model's previous failures resulted in a 6.1-point decrease at 1.5B (p=0.006), while execution feedback showed no significant advantage over the placebo. These results indicate that additional attempts, rather than feedback, enhance performance in smaller models.

Key facts

  • Study compares self-repair to blind resampling in code models
  • Placebo-controlled design on MBPP+ dataset
  • Models tested: 1.5B, 3B, 7B parameters
  • Four retry conditions: blind resampling, content-free failure notice, execution feedback, feedback with self-reflection
  • Blind resampling strongest below 7B, tied at 7B
  • Blind resampling uses 2.5-5.5x fewer tokens
  • Conditioning on failed attempt costs 6.1 points at 1.5B (p=0.006)
  • Execution feedback adds no measurable value over placebo

Entities

Institutions

  • arXiv

Sources