LLM repair agents fail mostly on type and code-context problems, and a hybrid static-analysis/LLM tool fixes 29 of 127 previously failed type-related patches.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
PAGENT: Learning to Patch Software Engineering Agents
LLM repair agents fail mostly on type and code-context problems, and a hybrid static-analysis/LLM tool fixes 29 of 127 previously failed type-related patches.