List your company

Tool Shortlisting on AppWorld v1.0 (test)

0.71R-precision (AZ)TabAgent
-0.00760.17870.3650.5513Feb 18, 2026

Evaluation results

MethodLinks
TabAgentTraining Supervision=Real+synth2026.020.710.660.90.960.610.950.930.9810.880.970.95110.92
DSR-FTEvaluation Protocol=Fine-tuned, Training Supervision=Real+synth2026.020.690.560.850.920.640.930.90.9810.850.950.930.9910.88
TabAgentTraining Supervision=Real-Only2026.020.570.580.660.620.70.910.880.9810.880.930.91110.9
Llama-3.1-8B-InstructBackbone=Llama-3.1-8B, Evaluation Protocol=Zero-Shot2026.020.560.450.380.70.670.560.50.650.710.670.560.50.650.730.69
DSR-FTEvaluation Protocol=Fine-tuned, Training Supervision=Real-Only2026.020.450.520.570.630.460.890.840.950.990.820.90.870.950.990.85
DSREvaluation Protocol=Zero-Shot2026.020.390.180.30.550.30.650.460.820.890.620.670.530.880.960.7
Llama-3.2-3B-InstructBackbone=Llama-3.2-3B, Evaluation Protocol=Zero-Shot2026.020.380.340.40.420.390.60.580.630.760.640.660.660.660.790.67
BM25Evaluation Protocol=Zero-Shot2026.020.280.190.350.420.280.480.510.540.720.60.540.580.570.740.71
Llama-3.2-1B-InstructBackbone=Llama-3.2-1B, Evaluation Protocol=Zero-Shot2026.020.020.030.060.070.090.290.270.290.450.330.320.290.330.460.34