List your company

Agricultural Agent Planning and Execution on AgriAgent Non-Zero

87.2Task FulfillmentAgriAgent
38.11250.85663.676.344Jan 13, 2026

Evaluation results

MethodLinks
AgriAgentModel=Qwen3-235B2026.0187.2—81.979.8
AgriAgentModel=DeepSeek-v3.12026.0185.1—80.275.3
AgriAgentModel=Qwen2.5-14B2026.0180.378.672.970.3
AgriAgentModel=Qwen3-32B2026.0178.579.678.471.3
AgriAgent (w/o feedback)Model=Qwen3-32B2026.0177.778.87770.6
AgriAgent (w/o feedback)Model=Qwen2.5-14B2026.0177.67872.466.8
AgriAgentModel=Qwen2.5-7B2026.0176.370.267.464.1
AgriAgent (w/o feedback)Model=AgriGPT-8B2026.0175.177.672.968.8
AgriAgentModel=AgriGPT-8B2026.0174.57966.965.5
plan-and-executeModel=Qwen3-32B2026.0173.678.153.863.3
AgriAgentModel=Qwen3-8B2026.0170.376.867.258.9
AgriAgent (w/o feedback)Model=Qwen3-8B2026.0169.377.16960
reactModel=Qwen2.5-14B2026.0169.374.637.851.3
plan-and-executeModel=Qwen2.5-7B2026.016769.334.148.6
plan-and-executeModel=Qwen2.5-14B2026.0164.976.937.553.4
AgriAgentModel=LLaMA3-8B2026.0163.574.855.753.6
plan-and-executeModel=AgriGPT-8B2026.016377.545.555.8
plan-and-executeModel=Qwen3-8B2026.0161.276.145.154
reactModel=Qwen2.5-7B2026.0158.966.729.743.2
reactModel=LLaMA3-8B2026.0152.242.428.645.3
reactModel=AgriGPT-8B2026.0150.571.732.642.3
AgriAgent (w/o feedback)Model=Qwen2.5-7B2026.0150.470.547.841.8
reactModel=Qwen3-8B2026.0149.673.831.544.8
reactModel=Qwen3-32B2026.0147.57030.144.6
AgriAgent (w/o feedback)Model=LLaMA3-8B2026.0144.174.645.239.6
plan-and-executeModel=LLaMA3-8B2026.014041.62040