Official model of SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning
liuqirui
neuqrui
·
AI & ML interests
ai safety
Recent Activity
updated a collection about 9 hours ago
SCOPE updated a collection about 9 hours ago
SCOPE updated a collection about 9 hours ago
SCOPEOrganizations
None yet
models 18
neuqrui/webshop-analyzer-qwen3-1.7b
Text Generation • 2B • Updated • 3
neuqrui/scope-alfworld-qwen2.5-7b
Text Generation • 8B • Updated • 3
neuqrui/alfworld-analyzer-qwen3-1.7b
Text Generation • 2B • Updated • 2
neuqrui/scope-alfworld-qwen2.5-3b
Text Generation • 3B • Updated • 3
neuqrui/webshop-analyzer-qwen2.5-7b
Text Generation • 8B • Updated • 2
neuqrui/scope-webshop-qwen2.5-3b
Text Generation • 3B • Updated • 6
neuqrui/alfworld-analyzer-qwen2.5-7b
Text Generation • 8B • Updated • 7
neuqrui/scope-webshop-qwen3-1.7b
Text Generation • 2B • Updated • 6
neuqrui/scope-alfworld-qwen3-1.7b
Text Generation • 2B • Updated • 1
neuqrui/webshop-analyzer-qwen2.5-3b
Text Generation • 3B • Updated • 85