Across five LLM-based SE tools and three models, 3-4 repair iterations capture most achievable gains, with diminishing returns thereafter.
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
-
Is Three the Magic Number? An Empirical Evaluation of LLM-Based Repair Loops
Across five LLM-based SE tools and three models, 3-4 repair iterations capture most achievable gains, with diminishing returns thereafter.