The official models and datasets for the paper "Understanding Tool-Integrated Reasoning"
Heng Lin
Heng1999
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
19 days ago
Reasoning with Sampling: Your Base Model is Smarter Than You Think
commented on
a paper
28 days ago
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
new activity
about 1 month ago
Heng1999/Qwen3-8B-TIR-ASPO:Is the base model of Qwen3-8B-TIR-ASPO Qwen3-8B or Qwen3-8B-base?
Organizations
None yet