By replaying each validation command on buggy, candidate, and gold-fix code, this study finds 46% of positive checks do not discriminate the bug, and a reminder alone explains part of the feedback benefit.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?
By replaying each validation command on buggy, candidate, and gold-fix code, this study finds 46% of positive checks do not discriminate the bug, and a reminder alone explains part of the feedback benefit.