Decision Making on DELIVERYBENCH
41.71Mean Hourly ProfitCoT+MemoryBank+None
Evaluation Results
| Method | Links | |
|---|---|---|
| CoT+MemoryBank+NoneReasoning=CoT, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 41.71 | |
| MAD+MemoryBank+ReflexionReasoning=MAD, Memory=MemoryBank, Reflection=Reflexion, Backbone=Qwen3.5-27B2026.06 | 39.45 | |
| CoT+SimpleMem+ReflexionReasoning=CoT, Memory=SimpleMem, Reflection=Reflexion, Backbone=Qwen3.5-27B2026.06 | 35.75 | |
| MAD+MemoryBank+Self-RefineReasoning=MAD, Memory=MemoryBank, Reflection=Self-Refine, Backbone=Qwen3.5-27B2026.06 | 35.29 | |
| Plan&Solve+MemoryBank+NoneReasoning=Plan&Solve, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 34.73 | |
| ReAct+MemoryBank+NoneReasoning=ReAct, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 34.7 | |
| MAD+MemoryBank+NoneReasoning=MAD, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 33.99 | |
| CoT+DC+NoneReasoning=CoT, Memory=DC, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 33.64 | |
| MAD+ChatDB+NoneReasoning=MAD, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 31.16 | |
| ReAct+OpenClaw+NoneReasoning=ReAct, Memory=OpenClaw, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 31.12 | |
| ReAct+DC+ReflexionReasoning=ReAct, Memory=DC, Reflection=Reflexion, Backbone=Qwen3.5-27B2026.06 | 31.04 | |
| MAD+MemoryBank+ReflexionReasoning=MAD, Memory=MemoryBank, Reflection=Reflexion, Backbone=Qwen3.5-9B2026.06 | 31.04 | |
| CoT+SimpleMem+Self-RefineReasoning=CoT, Memory=SimpleMem, Reflection=Self-Refine, Backbone=Qwen3.5-27B2026.06 | 30.07 | |
| MAD+DC+NoneReasoning=MAD, Memory=DC, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 30.01 | |
| MAD+ChatDB+NoneReasoning=MAD, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 29.8 | |
| ReAct+MemoryBank+ReflexionReasoning=ReAct, Memory=MemoryBank, Reflection=Reflexion, Backbone=Qwen3.5-27B2026.06 | 29.02 | |
| None+Base+NoneReasoning=None, Memory=Base, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 28.89 | |
| ReAct+ChatDB+NoneReasoning=ReAct, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 28.86 | |
| MAD+DC+NoneReasoning=MAD, Memory=DC, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 27.64 | |
| ReAct+Base+ReflexionReasoning=ReAct, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-27B2026.06 | 27.41 | |
| MAD+MemoryBank+NoneReasoning=MAD, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 26.94 | |
| CoT+SimpleMem+NoneReasoning=CoT, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 26.48 | |
| MAD+Base+NoneReasoning=MAD, Memory=Base, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 26.38 | |
| MAD+SimpleMem+NoneReasoning=MAD, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 25.91 | |
| CoT+Base+ReflexionReasoning=CoT, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-27B2026.06 | 25.7 | |
| CoT+Base+NoneReasoning=CoT, Memory=Base, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 25.62 | |
| ReAct+Base+Self-RefineReasoning=ReAct, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-27B2026.06 | 25.05 | |
| Plan&Solve+SimpleMem+NoneReasoning=Plan&Solve, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 24.1 | |
| MAD+Base+NoneReasoning=MAD, Memory=Base, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 23.98 | |
| CoT+Base+Self-RefineReasoning=CoT, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-27B2026.06 | 23.71 | |
| Plan&Solve+Base+Self-RefineReasoning=Plan&Solve, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-27B2026.06 | 22.02 | |
| Plan&Solve+DC+NoneReasoning=Plan&Solve, Memory=DC, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 21.78 | |
| MAD+SimpleMem+NoneReasoning=MAD, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 21.67 | |
| ReAct+SimpleMem+NoneReasoning=ReAct, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 21.45 | |
| CoT+ChatDB+NoneReasoning=CoT, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 21.32 | |
| Plan&Solve+Base+NoneReasoning=Plan&Solve, Memory=Base, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 20.91 | |
| ReAct+ChatDB+NoneReasoning=ReAct, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 19.84 | |
| CoT+MemoryBank+NoneReasoning=CoT, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 19.48 | |
| Plan&Solve+Base+NoneReasoning=Plan&Solve, Memory=Base, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 19.42 | |
| Plan&Solve+ChatDB+NoneReasoning=Plan&Solve, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 19.2 | |
| ReAct+Base+NoneReasoning=ReAct, Memory=Base, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 18.57 | |
| ReAct+Base+Self-RefineReasoning=ReAct, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-9B2026.06 | 18.36 | |
| ReAct+OpenClaw+NoneReasoning=ReAct, Memory=OpenClaw, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 18.22 | |
| Plan&Solve+Base+ReflexionReasoning=Plan&Solve, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-27B2026.06 | 18.15 | |
| CoT+SimpleMem+ReflexionReasoning=CoT, Memory=SimpleMem, Reflection=Reflexion, Backbone=Qwen3.5-9B2026.06 | 17.76 | |
| ReAct+DC+NoneReasoning=ReAct, Memory=DC, Reflection=None, Backbone=Qwen3.5-27B2026.06 | 17.44 | |
| ReAct+DC+ReflexionReasoning=ReAct, Memory=DC, Reflection=Reflexion, Backbone=Qwen3.5-9B2026.06 | 17.28 | |
| CoT+DC+NoneReasoning=CoT, Memory=DC, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 17.17 | |
| Plan&Solve+MemoryBank+NoneReasoning=Plan&Solve, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 15.69 | |
| ReAct+DC+NoneReasoning=ReAct, Memory=DC, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 14.95 | |
| ReAct+Base+ReflexionReasoning=ReAct, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-9B2026.06 | 14.69 | |
| CoT+SimpleMem+Self-RefineReasoning=CoT, Memory=SimpleMem, Reflection=Self-Refine, Backbone=Qwen3.5-9B2026.06 | 13.43 | |
| ReAct+MemoryBank+ReflexionReasoning=ReAct, Memory=MemoryBank, Reflection=Reflexion, Backbone=Qwen3.5-9B2026.06 | 12.65 | |
| ReAct+Base+NoneReasoning=ReAct, Memory=Base, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 12.64 | |
| CoT+Base+NoneReasoning=CoT, Memory=Base, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 12.62 | |
| MAD+MemoryBank+Self-RefineReasoning=MAD, Memory=MemoryBank, Reflection=Self-Refine, Backbone=Qwen3.5-9B2026.06 | 12.18 | |
| CoT+Base+Self-RefineReasoning=CoT, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-9B2026.06 | 11.95 | |
| Plan&Solve+ChatDB+NoneReasoning=Plan&Solve, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 11.32 | |
| CoT+ChatDB+NoneReasoning=CoT, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 11.2 | |
| Plan&Solve+Base+Self-RefineReasoning=Plan&Solve, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-9B2026.06 | 11.19 | |
| CoT+Base+ReflexionReasoning=CoT, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-9B2026.06 | 11.09 | |
| ReAct+SimpleMem+NoneReasoning=ReAct, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 9.59 | |
| Plan&Solve+DC+NoneReasoning=Plan&Solve, Memory=DC, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 9.43 | |
| Plan&Solve+SimpleMem+NoneReasoning=Plan&Solve, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 8.55 | |
| Plan&Solve+Base+ReflexionReasoning=Plan&Solve, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-9B2026.06 | 7.78 | |
| ReAct+MemoryBank+NoneReasoning=ReAct, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 7.49 | |
| None+Base+NoneReasoning=None, Memory=Base, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 7.13 | |
| CoT+SimpleMem+NoneReasoning=CoT, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-9B2026.06 | 3.16 | |
| CoT+ChatDB+NoneReasoning=CoT, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | 0 | |
| ReAct+Base+Self-RefineReasoning=ReAct, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-0.8B2026.06 | 0 | |
| CoT+Base+Self-RefineReasoning=CoT, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-0.8B2026.06 | 0 | |
| CoT+SimpleMem+Self-RefineReasoning=CoT, Memory=SimpleMem, Reflection=Self-Refine, Backbone=Qwen3.5-0.8B2026.06 | 0 | |
| CoT+SimpleMem+NoneReasoning=CoT, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -2.05 | |
| MAD+MemoryBank+Self-RefineReasoning=MAD, Memory=MemoryBank, Reflection=Self-Refine, Backbone=Qwen3.5-0.8B2026.06 | -2.5 | |
| None+Base+NoneReasoning=None, Memory=Base, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -2.89 | |
| CoT+MemoryBank+NoneReasoning=CoT, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -4.15 | |
| MAD+MemoryBank+NoneReasoning=MAD, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -4.35 | |
| ReAct+Base+ReflexionReasoning=ReAct, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-0.8B2026.06 | -4.54 | |
| ReAct+Base+NoneReasoning=ReAct, Memory=Base, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -4.55 | |
| Plan&Solve+Base+NoneReasoning=Plan&Solve, Memory=Base, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -4.65 | |
| Plan&Solve+SimpleMem+NoneReasoning=Plan&Solve, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -4.89 | |
| Plan&Solve+MemoryBank+NoneReasoning=Plan&Solve, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -5.97 | |
| Plan&Solve+Base+Self-RefineReasoning=Plan&Solve, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-0.8B2026.06 | -6.77 | |
| ReAct+SimpleMem+NoneReasoning=ReAct, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -6.86 | |
| Plan&Solve+MemoryBank+NoneReasoning=Plan&Solve, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -6.88 | |
| Plan&Solve+Base+NoneReasoning=Plan&Solve, Memory=Base, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -7.01 | |
| CoT+Base+ReflexionReasoning=CoT, Memory=Base, Reflection=Reflexion, Backbone=Qwen3.5-0.8B2026.06 | -7.1 | |
| Plan&Solve+SimpleMem+NoneReasoning=Plan&Solve, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -7.15 | |
| CoT+SimpleMem+ReflexionReasoning=CoT, Memory=SimpleMem, Reflection=Reflexion, Backbone=Qwen3.5-0.8B2026.06 | -7.32 | |
| ReAct+ChatDB+NoneReasoning=ReAct, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -7.47 | |
| CoT+MemoryBank+NoneReasoning=CoT, Memory=MemoryBank, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -7.47 | |
| CoT+Base+NoneReasoning=CoT, Memory=Base, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -7.63 | |
| ReAct+Base+Self-RefineReasoning=ReAct, Memory=Base, Reflection=Self-Refine, Backbone=Qwen3.5-2B2026.06 | -8.04 | |
| Plan&Solve+ChatDB+NoneReasoning=Plan&Solve, Memory=ChatDB, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -8.14 | |
| None+Base+NoneReasoning=None, Memory=Base, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -8.54 | |
| CoT+SimpleMem+NoneReasoning=CoT, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -8.61 | |
| ReAct+MemoryBank+ReflexionReasoning=ReAct, Memory=MemoryBank, Reflection=Reflexion, Backbone=Qwen3.5-2B2026.06 | -8.66 | |
| ReAct+OpenClaw+NoneReasoning=ReAct, Memory=OpenClaw, Reflection=None, Backbone=Qwen3.5-2B2026.06 | -8.72 | |
| Plan&Solve+DC+NoneReasoning=Plan&Solve, Memory=DC, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -8.92 | |
| ReAct+SimpleMem+NoneReasoning=ReAct, Memory=SimpleMem, Reflection=None, Backbone=Qwen3.5-0.8B2026.06 | -8.97 |