List your company

Science Simulation Task Completion on ScienceWorld Unseen

66.3Success RateImagine-and-Act
3.005619.437835.8752.3022Jun 1, 2026

Evaluation results

MethodLinks
Imagine-and-ActBackbone=DeepSeek-V4-Pro, Category=API-Called Models, Training-free=true2026.0666.3
ReActBackbone=DeepSeek-V4-Pro, Category=API-Called Models, Training-free=true2026.0662.8
COMAPBackbone=Qwen3-8B, Category=Co-evolving, Training-based=true2026.0656.95
Imagine-and-ActBackbone=GPT-5.4, Category=API-Called Models, Training-free=true2026.0655.8
ITPRBackbone=Qwen3-8B, Category=World Modeling, Training-free=true2026.0655.3
IWMBackbone=Qwen3-8B, Category=World Modeling, Training-free=true2026.0654.3
ReActBackbone=GPT-5.4, Category=API-Called Models, Training-free=true2026.0653.4
ReAct (w/ SFT)Backbone=Qwen3-8B, Category=Base Agent Planning, Training-based=true2026.0650.33
COMAPBackbone=Qwen3-4B, Category=Co-evolving, Training-based=true2026.0649.2
Imagine-and-ActBackbone=DeepSeek-V4-Flash, Category=API-Called Models, Training-free=true2026.0648.6
WKMBackbone=Qwen3-8B, Category=World Modeling, Training-free=true2026.0647.68
ReActBackbone=DeepSeek-V4-Flash, Category=API-Called Models, Training-free=true2026.0645.3
ITPRBackbone=Qwen3-4B, Category=World Modeling, Training-free=true2026.0643.2
Imagine-and-Act (w/ SFT)Backbone=Qwen3-8B, Category=Base Agent Planning, Training-based=true2026.0642.14
IWMBackbone=Qwen3-4B, Category=World Modeling, Training-free=true2026.0640.6
WKMBackbone=Qwen3-4B, Category=World Modeling, Training-free=true2026.0637.5
Imagine-and-Act (w/ SFT)Backbone=Qwen3-4B, Category=Base Agent Planning, Training-based=true2026.0636.7
ReAct (w/ SFT)Backbone=Qwen3-4B, Category=Base Agent Planning, Training-based=true2026.0634.2
RAPBackbone=Qwen3-8B, Category=Test-time Evolving, Training-free=true2026.0627.14
ITPIBackbone=Qwen3-8B, Category=Test-time Evolving, Training-free=true2026.0619.2
Imagine-and-ActBackbone=Qwen3-8B, Category=Base Agent Planning, Training-free=true2026.0615.6
ITPIBackbone=Qwen3-4B, Category=Test-time Evolving, Training-free=true2026.0614.2
RAPBackbone=Qwen3-4B, Category=Test-time Evolving, Training-free=true2026.0612.5
ReflexionBackbone=Qwen3-8B, Category=Test-time Evolving, Training-free=true2026.0612.1
ReActBackbone=Qwen3-8B, Category=Base Agent Planning, Training-free=true2026.068.61
ReflexionBackbone=Qwen3-4B, Category=Test-time Evolving, Training-free=true2026.068.4
Imagine-and-ActBackbone=Qwen3-4B, Category=Base Agent Planning, Training-free=true2026.067.9
ReActBackbone=Qwen3-4B, Category=Base Agent Planning, Training-free=true2026.065.44