ResearchBenchmarksMulti-hop Tool-use on ToolHop rand (test)Follow31.1AccuracyRimRule26.31627.55828.830.042Dec 31, 2025Evaluation ResultsMethodMethodLinksAccuracyRimRuleAdaptation Method=Recu...Adaptation Method=Recursive Induction of Symbolic Rules2025.1231.1Few-shotAdaptation Method=Few-...Adaptation Method=Few-shot prompting2025.1229.9SEEAdaptation Method=Self...Adaptation Method=Self-Evolutionary Evaluation2025.1227.6Zero-shotAdaptation Method=Zero...Adaptation Method=Zero-shot prompting2025.1226.5