ResearchBenchmarksTask Planning on Shortsighted Monkey (Scene 8)Follow100Success RatePlanORN58.469.28090.8Feb 9, 2026Evaluation ResultsMethodMethodLinksSuccess RateAverage StepsAverage Time (s)Average TokensTime to SuccessTokens per SuccessPlanORNAgent=PlanORN*Agent=PlanORN*2026.0210022.494.34—94.34—ORAgent=OR*Agent=OR*2026.029429.683.31—88.62—ORNAgent=ORN*Agent=ORN*2026.028826.296.63—109.8—ReActAgent=ReActAgent=ReAct2026.028632.4311.66—361.24—BasicAgent=BasicAgent=Basic2026.02663878.81—119.41—MLDTAgent=MLDTAgent=MLDT2026.026036.882.44—137.4—