ResearchBenchmarksRobotic Task Planning on Classic (Scene 2)Robotic Task Planning on Classic (Scene 2)Follow97Success RateOR80.3684.688993.32Feb 9, 2026Evaluation resultsMethodMethodLinksSuccess RateAverage StepsAverage Time (s)Average TokensTime to Success (T2S)Tokens per Success (T2S)OR2026.029722.561.65—63.56—ReAct2026.028730.9232.64—267.4—Basic2026.028623.645.74—53.18—MLDT2026.028528.665.51—77.07—PlanORN2026.028534.1166.6—196—ORN2026.028129.1109.63—135.34—