SOURCE-LINKED INTELLIGENCE

Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Fault localization can focus a code model's repair on the statements a failing test implicates, but a targeted edit may succeed merely because it is small, and a second model call may succeed without using the failure at all. We separate these explanations with three arms applied to the same failed candidate: blind whole-solution resampling, spectrum-based localization followed by suspect-span infilling, and same-length infilling at a disjoint random code span. Across three frozen 26-32B models, three benchmarks and 488 failing candidates, plus a separately declared 24B fourth model from a thi

Read original source ↗ Open in workspace

recordType

paper

region

Global