ResearchTasksMulti-fidelity bandit optimizationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLLM-as-a-judge residual-mismatch Λ=128000 (test)TACC4,023.4Mean Cost-Weighted Pseudo-Regret4May 12, 2026
LLM-as-a-judge residual-mismatch Λ=128000 (test)TACC4,023.4Mean Cost-Weighted Pseudo-Regret4May 12, 2026