[2512.13607] Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models

Computer Science > Computation and Language arXiv:2512.13607 (cs) [Submitted on 15 Dec 2025 (v1), last revised 27 Mar 2026 (this version, v2)] Title:Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models Authors:Boxin Wang, Chankyu Lee, Nayeon Lee, Sheng-Chieh Lin, Wenliang Dai, Yang Chen, Yangyi Chen, Zhuolin Yang, Zihan Liu, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping View a PDF of the paper titled Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models, by Boxin Wang and 11 other authors View PDF HTML (experimental) Abstract:Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response lengths and verification latency. Such variability complicates the RL infrastructure, slows training, and makes training curriculum (e.g., response length extension) and hyperparameter selection challenging. In this work, we propose cascaded domain-wise reinforcement learning (Cascade RL) to develop Nemotron-Cascade, capable of operating in both instruct and deep thinking modes, without any performance gap relative to a thinking-only counterpart. Departing from conventional approaches that blend heterogeneous prompts from different domains, Cascade RL orchestrates sequential, domain-wise RL, reducing engineering complexity and delivering state-of-the-art performance across a wide range of benchmarks...