List your company

Planning on TravelPlanner #180 (val)

95.64CS-MicroHiMAP-Travel
45.678458.649271.6284.5908Aug 19, 2024Nov 20, 2024Feb 22, 2025May 27, 2025Aug 29, 2025Dec 1, 2025Mar 5, 2026

Evaluation results

MethodLinks
HiMAP-TravelBackbone=Qwen3-8B2026.0395.64—73.6176.8563.3352.78—100100
HiMAP-TravelBackbone=Qwen3-4B2026.0395.57—72.3670.8959.1748.61—100100
AutoRefineAugmentation=ReAct2026.0194.2410057.7852.8643.89—40——
AutoRefine2026.0192.7110054.4449.7638.89—35.56——
DeepTravelBackbone=Qwen3-8B2026.0392.6—67.6471.4358.6145.56—97.699.4
DeepTravelBackbone=Qwen3-4B2026.0390—59.5863.1549.4435.28—96.898.2
MTPBackbone=GPT-4 w/ hint2026.0387.29—43.3347.1446.6733.33—96.797.4
ATLASAugmentation=Hint2026.0185.4210048.3360.7147.22—33.33——
ATLAS2026.0183.410037.7856.4338.89—23.33——
MegaAgentMode=sole-planning2024.0881.8810027.2240.4823.8910———
Direct GPT-4-TurboBackbone=GPT-4-Turbo, Strategy=Direct, Mode=sole-planning2024.0880.410017.247.122.24.4———
ReAct2026.0179.3810022.7856.1938.89—11.67——
PMC2026.0176.1196.6721.6739.5230.56—14.44——
ReActAugmentation=Reflexion2026.0174.7999.4418.3345.4828.33—10——
ReActAugmentation=EvoAgent2026.0174.0899.4419.7138.0520.33—8.03——
Direct Mixtral-8×7B-MoEBackbone=Mixtral-8×7B-MoE, Strategy=Direct, Mode=sole-planning2024.0868.110053.31.10———
CoT GPT-3.5-TurboBackbone=GPT-3.5-Turbo, Strategy=Chain-of-Thought, Mode=sole-planning2024.0866.31003.311.950———
Direct Gemini ProBackbone=Gemini Pro, Strategy=Direct, Mode=sole-planning2024.086593.98.39.34.40.6———
Direct GPT-3.5-TurboBackbone=GPT-3.5-Turbo, Strategy=Direct, Mode=sole-planning2024.0860.21004.4112.80———
Reflexion GPT-3.5-TurboBackbone=GPT-3.5-Turbo, Strategy=Reflexion, Mode=sole-planning2024.0853.893.92.8112.80———
ATLASBackbone=Gemini-2.5-Pro2026.0348.33—88.5482.6274.4444.44—100100
ReAct GPT-3.5-TurboBackbone=GPT-3.5-Turbo, Strategy=ReAct, Mode=sole-planning2024.0847.682.23.911.46.70.6———