This repository provides Thinking Outside the Box-trained models for mathematical reasoning and WebShop tasks. It includes the SFT and RL checkpoints.
-
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Paper • 2609.39578 • Published • 6 -
wangminghan/Box2-Bench
Viewer • Updated • 650 • 80 -
ElvisWang111/Qwen3-4B-OutsideTheBox-SFT
Text Generation • 196k • Updated • 241 -
ElvisWang111/Qwen3-4B-OutsideTheBox-RL
Text Generation • 196k • Updated • 161
