Shu Zhao PRO

TreezzZ's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 5 days ago

Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation

Paper • 2610.28586 • Published 6 days ago

updated a collection 5 days ago

R2S: Rollout-to-Scorer Distillation

Collection

R2S teachers & students (ALFWorld, ScienceWorld, WebShop). Paper: arxiv.org/abs/2610.28586. Code: github.com/Tree-Shu-Zhao/miles-agent, tag r2s • 25 items • Updated 5 days ago

updated 18 models 5 days ago

TreezzZ/r2s-webshop-qwen3-8b-student

Text Generation • 8B • Updated 5 days ago • 318

TreezzZ/r2s-webshop-qwen3-30b-a3b-teacher-for-qwen3-8b

Text Generation • 8B • Updated 5 days ago • 285

TreezzZ/r2s-webshop-qwen3-4b-student

Text Generation • 4B • Updated 5 days ago • 263

TreezzZ/r2s-webshop-qwen3-30b-a3b-teacher-for-qwen3-4b

Text Generation • 8B • Updated 5 days ago • 275

TreezzZ/r2s-webshop-qwen3.5-4b-student

Text Generation • 5B • Updated 5 days ago • 269

TreezzZ/r2s-webshop-qwen3.5-9b-teacher-for-qwen3.5-4b

Text Generation • 9B • Updated 5 days ago • 254

TreezzZ/r2s-webshop-qwen3.5-2b-student

Text Generation • 2B • Updated 5 days ago • 262

TreezzZ/r2s-webshop-qwen3.5-9b-teacher-for-qwen3.5-2b

Text Generation • 9B • Updated 5 days ago • 262

TreezzZ/r2s-scienceworld-qwen3-8b-student

Text Generation • 8B • Updated 5 days ago • 301

TreezzZ/r2s-scienceworld-qwen3-30b-a3b-teacher-for-qwen3-8b

Text Generation • 8B • Updated 5 days ago • 265

TreezzZ/r2s-scienceworld-qwen3-4b-student

Text Generation • 4B • Updated 5 days ago • 264

TreezzZ/r2s-scienceworld-qwen3-30b-a3b-teacher-for-qwen3-4b

Text Generation • 8B • Updated 5 days ago • 250

TreezzZ/r2s-scienceworld-qwen3.5-4b-student

Text Generation • 5B • Updated 5 days ago • 262

TreezzZ/r2s-scienceworld-qwen3.5-9b-teacher-for-qwen3.5-4b

Text Generation • 9B • Updated 5 days ago • 237

TreezzZ/r2s-scienceworld-qwen3.5-2b-student

Text Generation • 2B • Updated 5 days ago • 245

TreezzZ/r2s-scienceworld-qwen3.5-9b-teacher-for-qwen3.5-2b

Text Generation • 9B • Updated 5 days ago • 242

TreezzZ/r2s-alfworld-qwen3-8b-student

Text Generation • 8B • Updated 5 days ago • 247

TreezzZ/r2s-alfworld-qwen3-30b-a3b-teacher-for-qwen3-8b

Text Generation • 8B • Updated 5 days ago • 236