List your company

Science Simulation Task Completion on ScienceWorld Seen

69.8Success RateImagine-and-Act
3.780820.920438.0655.1996Jun 1, 2026

Evaluation results

MethodLinks
Imagine-and-ActBackbone=DeepSeek-V4-Pro, Category=API-Called Models, Training-free=true2026.0669.8
ReActBackbone=DeepSeek-V4-Pro, Category=API-Called Models, Training-free=true2026.0666.5
COMAPBackbone=Qwen3-8B, Category=Co-evolving, Training-based=true2026.0661.85
Imagine-and-ActBackbone=GPT-5.4, Category=API-Called Models, Training-free=true2026.0660.7
WKMBackbone=Qwen3-8B, Category=World Modeling, Training-free=true2026.0660.31
ITPRBackbone=Qwen3-8B, Category=World Modeling, Training-free=true2026.0660.2
IWMBackbone=Qwen3-8B, Category=World Modeling, Training-free=true2026.0659.27
Imagine-and-Act (w/ SFT)Backbone=Qwen3-8B, Category=Base Agent Planning, Training-based=true2026.0658.62
ReActBackbone=GPT-5.4, Category=API-Called Models, Training-free=true2026.0658.1
ReAct (w/ SFT)Backbone=Qwen3-8B, Category=Base Agent Planning, Training-based=true2026.0657.21
COMAPBackbone=Qwen3-4B, Category=Co-evolving, Training-based=true2026.0653.9
Imagine-and-ActBackbone=DeepSeek-V4-Flash, Category=API-Called Models, Training-free=true2026.0652.7
ITPRBackbone=Qwen3-4B, Category=World Modeling, Training-free=true2026.0649.85
ReActBackbone=DeepSeek-V4-Flash, Category=API-Called Models, Training-free=true2026.0649.6
IWMBackbone=Qwen3-4B, Category=World Modeling, Training-free=true2026.0645.2
WKMBackbone=Qwen3-4B, Category=World Modeling, Training-free=true2026.0643.7
Imagine-and-Act (w/ SFT)Backbone=Qwen3-4B, Category=Base Agent Planning, Training-based=true2026.0642.3
ReAct (w/ SFT)Backbone=Qwen3-4B, Category=Base Agent Planning, Training-based=true2026.0639.5
ITPIBackbone=Qwen3-8B, Category=Test-time Evolving, Training-free=true2026.0619.58
Imagine-and-ActBackbone=Qwen3-8B, Category=Base Agent Planning, Training-free=true2026.0616.8
RAPBackbone=Qwen3-8B, Category=Test-time Evolving, Training-free=true2026.0615.46
ITPIBackbone=Qwen3-4B, Category=Test-time Evolving, Training-free=true2026.0613.6
ReflexionBackbone=Qwen3-8B, Category=Test-time Evolving, Training-free=true2026.0612.5
RAPBackbone=Qwen3-4B, Category=Test-time Evolving, Training-free=true2026.0610.8
ReActBackbone=Qwen3-8B, Category=Base Agent Planning, Training-free=true2026.069.79
ReflexionBackbone=Qwen3-4B, Category=Test-time Evolving, Training-free=true2026.068.9
Imagine-and-ActBackbone=Qwen3-4B, Category=Base Agent Planning, Training-free=true2026.068.6
ReActBackbone=Qwen3-4B, Category=Base Agent Planning, Training-free=true2026.066.32