List your company

Agricultural Agent Planning and Execution on AgriAgent Full set

100CoverageAgriAgent
-3.58423.30850.277.092Jan 13, 2026

Evaluation results

MethodLinks
AgriAgentModel=Qwen3-32B2026.0110078.673.178.377.679.676.770.9
AgriAgentModel=Qwen3-235B2026.01100100100—87.2—81.979.8
AgriAgentModel=Qwen3-8B2026.0198.749.750.578.668.976.866.157.6
AgriAgentModel=AgriGPT-8B2026.0198.157.258.67072.97962.263.9
AgriAgentModel=Qwen2.5-14B2026.0196.974.180.95077.578.667.567.9
AgriAgent (w/o feedback)Model=Qwen3-8B2026.0196.766.266.478.666.977.162.858
AgriAgent (w/o feedback)Model=Qwen3-32B2026.0196.674.16973.675.278.872.768.4
AgriAgentModel=DeepSeek-v3.12026.019594.795—80.9—73.871.5
AgriAgentModel=Qwen2.5-7B2026.0194.471.975.755.571.970.261.960.5
AgriAgent (w/o feedback)Model=AgriGPT-8B2026.0191.962.863.872.268.877.663.963.1
AgriAgentModel=LLaMA3-8B2026.0190.967.376.635.855.574.847.347.9
AgriAgent (w/o feedback)Model=Qwen2.5-14B2026.0169.15153.148.953.57848.546.1
reactModel=Qwen2.5-14B2026.0162.49.24.34643.174.620.331.7
plan-and-executeModel=Qwen2.5-7B2026.0159.31.3104239.669.31828.9
plan-and-executeModel=Qwen2.5-14B2026.0156.73.18.43236.676.919.430.3
AgriAgent (w/o feedback)Model=Qwen2.5-7B2026.0155.937.339.254.337.570.533.931.2
reactModel=AgriGPT-8B2026.0153.80.82.66226.771.714.222.6
AgriAgent (w/o feedback)Model=LLaMA3-8B2026.0149.531.939.331.521.874.621.819.8
plan-and-executeModel=Qwen3-32B2026.0149.48.511.26135.478.124.430.3
plan-and-executeModel=AgriGPT-8B2026.01486.38.8652977.520.927
reactModel=Qwen3-8B2026.0143.70.30.36521.573.812.319.6
plan-and-executeModel=Qwen3-8B2026.0143.34.86.76126.476.118.123.5
reactModel=Qwen3-32B2026.0117.80.71.3607.9704.67.9
reactModel=Qwen2.5-7B2026.0112.10035766.72.24.7
reactModel=LLaMA3-8B2026.016.30.3013.442.41.73
plan-and-executeModel=LLaMA3-8B2026.010.4002.90.241.60.10.2