List your company

Travel Planning on TravelPlanner

14.8Average Tokens UsedToRL
-131.4032855.46841,842.342,829.2116May 22, 2025Jun 17, 2025Jul 14, 2025Aug 10, 2025Sep 5, 2025Oct 2, 2025Oct 29, 2025

Evaluation results

MethodLinks
ToRLBackbone=Qwen-2.5-7B-Instruct2025.1014.8——86.7—
AgentFlowBackbone=Qwen-2.5-7B-Instruct2025.1016.2——91.7—
SimpleTIRBackbone=Qwen-2.5-7B-Instruct2025.1016.2——88.9—
GRPOfmBackbone=Qwen-2.5-7B-Instruct2025.1016.4——90.6—
ARPOfmBackbone=Qwen-2.5-7B-Instruct2025.1016.7——92.2—
PORToolBackbone=Qwen-2.5-7B-Instruct2025.1016.7——92.8—
PLAN-AND-BUDGET + LinearModel=DeepSeek-R1-Distill-Qwen-32B2025.051,136.1819.560.34——
PLAN-AND-BUDGET + CosineModel=DeepSeek-R1-Distill-Qwen-32B2025.051,140.7920.220.36——
PLAN-AND-BUDGET + PolynomialModel=DeepSeek-R1-Distill-Llama-70B2025.051,148.1432.670.93——
PLAN-AND-BUDGET + PolynomialModel=DeepSeek-R1-Distill-Qwen-32B2025.051,148.5323.110.47——
PLAN-AND-BUDGET + ExponentialModel=DeepSeek-R1-Distill-Qwen-32B2025.051,156.6421.440.4——
Direct Global BudgetModel=DeepSeek-R1-Distill-Qwen-32B2025.051,158.8113.780.16——
PLAN-AND-BUDGET + LinearModel=DeepSeek-R1-Distill-Llama-70B2025.051,162.2431.670.86——
PLAN-AND-BUDGET + CosineModel=DeepSeek-R1-Distill-Llama-70B2025.051,173.9631.670.85——
PLAN-AND-BUDGET + ExponentialModel=DeepSeek-R1-Distill-Llama-70B2025.051,187.85320.86——
PLAN-AND-BUDGET + WeightedModel=DeepSeek-R1-Distill-Llama-70B2025.051,197.3229.670.74——
Direct Global BudgetModel=DeepSeek-R1-Distill-Llama-70B2025.051,215.2924.330.49——
Planned Global BudgetModel=DeepSeek-R1-Distill-Llama-70B2025.051,220.4130.670.77——
PLAN-AND-BUDGET + WeightedModel=DeepSeek-R1-Distill-Qwen-32B2025.051,222.0923.330.45——
PLAN-AND-BUDGET + UniformModel=DeepSeek-R1-Distill-Qwen-32B2025.051,227.9920.670.35——
PLAN-AND-BUDGET + UniformModel=DeepSeek-R1-Distill-Llama-70B2025.051,232.9831.560.81——
Planned Global BudgetModel=DeepSeek-R1-Distill-Qwen-32B2025.051,241.1922.560.41——
Direct Global BudgetModel=o4-mini2025.051,248.538.330.056——
PLAN-AND-BUDGET + CosineModel=o4-mini2025.051,252.069.790.077——
PLAN-AND-BUDGET + PolynomialModel=o4-mini2025.051,266.1111.490.104——
PLAN-AND-BUDGET + LinearModel=o4-mini2025.051,306.5411.660.103——
PLAN-AND-BUDGET + ExponentialModel=o4-mini2025.051,307.879.910.075——
Planned VanillaModel=DeepSeek-R1-Distill-Qwen-32B2025.051,343.6720.220.3——
PLAN-AND-BUDGET + UniformModel=o4-mini2025.051,345.32110.09——
PLAN-AND-BUDGET + WeightedModel=o4-mini2025.051,353.6710.910.088——
Direct VanillaModel=DeepSeek-R1-Distill-Llama-70B2025.051,361.3726.220.5——
Planned Global BudgetModel=o4-mini2025.051,392.117.190.037——
Direct VanillaModel=DeepSeek-R1-Distill-Qwen-32B2025.051,430.1414.330.14——
Planned VanillaModel=DeepSeek-R1-Distill-Llama-70B2025.051,464.530.670.64——
Direct VanillaModel=o4-mini2025.051,559.6511.580.086——
Planned VanillaModel=o4-mini2025.051,640.4612.20.091——
PLAN-AND-BUDGET + CosineModel=QwQ-32B2025.052,496.4636.180.52——
PLAN-AND-BUDGET + PolynomialModel=QwQ-32B2025.052,511.35350.49——
Direct Global BudgetModel=QwQ-32B2025.052,530.0430.780.37——
PLAN-AND-BUDGET + LinearModel=QwQ-32B2025.052,671.734.550.45——
PLAN-AND-BUDGET + ExponentialModel=QwQ-32B2025.052,724.2335.440.46——
PLAN-AND-BUDGET + WeightedModel=QwQ-32B2025.052,842.7433.890.4——
PLAN-AND-BUDGET + UniformModel=QwQ-32B2025.052,854.24360.45——
Planned Global BudgetModel=QwQ-32B2025.053,199.5835.220.39——
Direct VanillaModel=QwQ-32B2025.053,432.3334.890.35——
Planned VanillaModel=QwQ-32B2025.053,669.8837.220.38——