Showing cs.AIShow all
3 papers · 1 filter
cs.AI2025
Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE
Anxiang Zeng, Haibo Zhang, Hailing Zhang +13
We present CompassMax-V3-Thinking, a hundred-billion-scale MoE reasoning model trained with a new RL framework built on one principle: each prompt must matter. Scaling RL to this s…
cs.AI2025
STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization
Yuhan Chen, Yuxuan Liu, Long Zhang +3
Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training…
cs.AI2025
Compass-Thinker-7B Technical Report
Anxiang Zeng, Haibo Zhang, Kaixiang Mo +6
Recent R1-Zero-like research further demonstrates that reasoning extension has given large language models (LLMs) unprecedented reasoning capabilities, and Reinforcement Learning i…