ResearchBenchmarkstask4 on puzzle 4x6Follow23Success RateTRL-0.925.2911.517.71Oct 26, 2025Evaluation ResultsMethodMethodLinksSuccess RateTRL2025.1023MC2025.105TD2025.101FBC2025.100IQL2025.100CRL2025.100SAC+BC2025.100QRL2025.100TDP2025.100COE2025.100