ResearchBenchmarksTask Planning on Shortsighted Monkey (Scene 7)Follow100SRBasic94.896.1597.598.85Feb 9, 2026Evaluation ResultsMethodMethodLinksSRAvg StepsAvg Time (s)Avg TokensTime to Success (s)Tokens to SuccessBasicAgent=BasicAgent=Basic2026.021007.615.05—15.05—ORAgent=OR*Agent=OR*2026.021007.616.15—16.15—ReActAgent=ReActAgent=ReAct2026.02998.753.46—54—ORNAgent=ORN*Agent=ORN*2026.02998.320.71—20.92—MLDTAgent=MLDTAgent=MLDT2026.02968.423.33—24.3—PlanORNAgent=PlanORN*Agent=PlanORN*2026.02959.939.45—41.52—