A constrained, feedback-augmented, component-wise harness evolution loop improves coding agent Pass@1 on SWE-bench Verified and transfers to held-out tasks and another base model.
HEAL : An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
A constrained, feedback-augmented, component-wise harness evolution loop improves coding agent Pass@1 on SWE-bench Verified and transfers to held-out tasks and another base model.