HARBOR formalizes harness optimization as constrained noisy Bayesian optimization over mixed-variable spaces and reports a case study where it outperforms manual tuning on a production coding agent.
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?ICLR, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HARBOR: Automated Harness Optimization
HARBOR formalizes harness optimization as constrained noisy Bayesian optimization over mixed-variable spaces and reports a case study where it outperforms manual tuning on a production coding agent.