A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning
Paper
•
2507.08267
•
Published
•
10
•
2
Inoue Yuichi
Inoichan
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive
Branching Tree Search
authored
a paper
about 1 month ago
A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy
with SFT and Efficiency with Reinforcement Learning
Organizations
commented
a
paper
about 1 month ago