SWE-Doctor generates multi-faceted BRTs, derives runtime diagnoses from their executions, and uses the diagnoses to guide patch generation, raising average resolution rates to 75.7% on SWE-bench Verified and 59.4% on SWE-bench Pro.
Otter: Generating tests from issues to validate SWE patches,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests
SWE-Doctor generates multi-faceted BRTs, derives runtime diagnoses from their executions, and uses the diagnoses to guide patch generation, raising average resolution rates to 75.7% on SWE-bench Verified and 59.4% on SWE-bench Pro.