Year: 2026
Type: preprint
Abstract: We present PCL-Reasoner-V1.5, a 32-billion-parameter large language model (LLM) for mathematical reasoning. The model is built upon Qwen2.5-32B and refined via supervised fine-tuning (SFT) followed by reinforcement learning (RL). A central innovation is our proposed offline RL method, which provides superior training stability and efficiency over standard online RL methods such as GRPO. Our model achieves state-of-the-art performance among models post-trained on Qwen2.5-32B, attaining average accuracies of 90.9% on AIME 2024 and 85.6% on AIME 2025. Our work demonstrates offline RL as a stable and efficient paradigm for advancing reasoning in LLMs. All experiments were conducted on Huawei Ascend 910C NPUs.
Source: arXiv (Cornell University)
Authors: Lu, Yao, Fan, Dengdong, Nie, Jianzheng, Xu, Fan, Chen, Jie, Zhou, Bin, Tian, Yonghong
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7125388372
Cites:
Cited by:
Related to: