ResearchBenchmarkstool-redundancy on CMA (train)tool-redundancy on CMA (train)Follow1KappaSPEAR0.950.97511.025May 25, 2026Evaluation resultsMethodMethodLinksKappaSPEARN (best-of-N)=3, 5, Ag...N (best-of-N)=3, 5, Agent Model=GPT-5.42026.051