Score: 0

Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning

Published: March 20, 2025 | arXiv ID: 2503.15952v2

By: Chen Li, Nazhou Liu, Kai Yang

Potential Business Impact:

Makes AI smarter and faster at thinking.

Business Areas:
A/B Testing Data and Analytics

Since DeepSeek-R1 popularized, Group Relative Policy Optimization (GRPO) has become the core part of training Reasoning LLMs. However, we find some deficiency that influences RL stability and inference efficiency, like zero-variance in advantage estimation. Thus, we propose Adaptive Group Policy Optimization (AGPO) which contains a simple but effective modification: a revised objective function to mitigate training fluctuation and zero advantage. The experiments demonstrate our method achieves more stable training and superior performance with significantly fewer tokens in reasoning steps.

Page Count
5 pages

Category
Computer Science:
Computation and Language