Agent explanation quality can be scored automatically with LLM questionnaires, and this score ranks agents differently from SWE-bench Verified.
ExplainBench: Evaluating Code Expla- nations from Agents
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
-
ExplainBench: Evaluating Code Explanations from Agents
Agent explanation quality can be scored automatically with LLM questionnaires, and this score ranks agents differently from SWE-bench Verified.