The first empirical study of test overfitting shows that auto-generated tests from issues can lead to code that passes observed tests but misses important cases or breaks functionality in SWE-bench issue resolution.
Refactoring Runaway
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.SE 3representative citing papers
Clotho ranks LLM test inputs by failure likelihood using a Gaussian mixture model over pre-generation hidden states of passing inputs, reaching 0.716 ROC-AUC with 5.4% labelling and transferring from open-weight to proprietary LLMs.
Empirical study finds coding agents produce fewer and less intense tangled refactorings than humans on Multi-SWE-bench; a refactoring-aware refinement improves compilability from 19.34% to 38.33% and resolves 2.79% more issues.
citing papers explorer
-
Investigating Test Overfitting on SWE-bench
The first empirical study of test overfitting shows that auto-generated tests from issues can lead to code that passes observed tests but misses important cases or breaks functionality in SWE-bench issue resolution.
-
Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
Clotho ranks LLM test inputs by failure likelihood using a Gaussian mixture model over pre-generation hidden states of passing inputs, reaching 0.716 ROC-AUC with 5.4% labelling and transferring from open-weight to proprietary LLMs.
-
"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution
Empirical study finds coding agents produce fewer and less intense tangled refactorings than humans on Multi-SWE-bench; a refactoring-aware refinement improves compilability from 19.34% to 38.33% and resolves 2.79% more issues.