ResearchBenchmarksManipulation on OGBench puzzle-4x4-noisyFollow56Success RateORS-2.2412.882843.12Apr 22, 2026Evaluation ResultsMethodMethodLinksSuccess RateORSseeds=8, test-time goa...seeds=8, test-time goals=52026.0456Go-Freshseeds=8, test-time goa...seeds=8, test-time goals=52026.0450GC-IQLseeds=8, test-time goa...seeds=8, test-time goals=52026.0429GC-IVLseeds=8, test-time goa...seeds=8, test-time goals=52026.0420GCBCseeds=8, test-time goa...seeds=8, test-time goals=52026.040QRLseeds=8, test-time goa...seeds=8, test-time goals=52026.040CRLseeds=8, test-time goa...seeds=8, test-time goals=52026.040