arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.19220cs.CLcs.AIcs.LG
收藏

Nemotron-Cascade 2:基于级联强化学习和多领域在线蒸馏的后训练大语言模型

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Zhuolin Yang, Zihan Liu, Yang Chen, Wenliang Dai, Boxin Wang, Sheng-Chieh Lin, Chankyu Lee, Yangyi Chen, Dongfu Jiang, Jiafan He, Renjie Pi, Grace Lam, Nayeon L… 展开作者

Zhuolin Yang, Zihan Liu, Yang Chen, Wenliang Dai, Boxin Wang, Sheng-Chieh Lin, Chankyu Lee, Yangyi Chen, Dongfu Jiang, Jiafan He, Renjie Pi, Grace Lam, Nayeon Lee, Alexander Bukharin, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

AI总结:

Nemotron-Cascade 2是一款30B MoE模型,通过级联强化学习和多领域在线蒸馏提升推理和智能体能力,在2025年国际数学奥林匹克竞赛、国际信息学奥林匹克竞赛和ICPC世界总决赛中达到金奖水平,参数更少性能更强。

摘要:

我们介绍了Nemotron-Cascade 2,一个具有30B MoE架构和3B激活参数的开源模型,其推理能力和强大的智能体能力处于行业领先水平。尽管其体积紧凑,但其数学和编程推理性能接近前沿的开源模型。它是继DeepSeekV3.2-Speciale-671B-A37B之后,第二个达到2025年国际数学奥林匹克竞赛(IMO)、国际信息学奥林匹克竞赛(IOI)和ICPC世界总决赛金奖水平的开源大语言模型,展示了在20倍更少参数的情况下显著的高智能密度。与Nemotron-Cascade 1相比,关键技术进步包括:在精心编纂的数据集上完成SFT后,我们大幅扩展了级联强化学习,以覆盖更广泛的推理和智能体领域。此外,我们引入了多领域在线策略蒸馏,从每个领域的最强中间教师模型中进行蒸馏,从而能够高效地恢复基准回归并保持持续的性能提升。我们发布了模型检查点和训练数据集的集合。

英文摘要:

We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical and coding reasoning performance approaches that of frontier open models. It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad (IMO), the International Olympiad in Informatics (IOI), and the ICPC World Finals, demonstrating remarkably high intelligence density with 20x fewer parameters. In contrast to Nemotron-Cascade 1, the key technical advancements are as follows. After SFT on a meticulously curated dataset, we substantially expand Cascade RL to cover a much broader spectrum of reasoning and agentic domains. Furthermore, we introduce multi-domain on-policy distillation from the strongest intermediate teacher models for each domain throughout the Cascade RL process, allowing us to efficiently recover benchmark regressions and sustain strong performance gains along the way. We release the collection of model checkpoint and training data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑