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

arXiv: https://arxiv.org/abs/2603.19220 · HTML: https://mlsanity.com/paper/2603.19220/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- First posted on arXiv 19 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Mixture-of-experts / [MoE in reinforcement learning and robotics](https://mlsanity.com/moe/moe-in-reinforcement-learning-and-robotics/)
- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Built on by (most cited first, 30 of 60)

- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026)
- [Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe](https://mlsanity.com/paper/2605.03677/) (2026)
- [Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2606.15007/) (2026)
- [KL for a KL: On-Policy Distillation with Control Variate Baseline](https://mlsanity.com/paper/2605.07865/) (2026)
- [Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation](https://mlsanity.com/paper/2605.16826/) (2026)
- [Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation](https://mlsanity.com/paper/2605.27115/) (2026)
- [Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation](https://mlsanity.com/paper/2606.13657/) (2026)
- [PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation](https://mlsanity.com/paper/2606.17199/) (2026)
- [Rethinking Privileged Information in On-Policy Self-Distillation](https://mlsanity.com/paper/2608.18271/) (2026)
- [OneReason Technical Report](https://mlsanity.com/paper/2606.06260/) (2026)
- [UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents](https://mlsanity.com/paper/2607.04425/) (2026)
- [Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning](https://mlsanity.com/paper/2604.07941/) (2026)
- [FLARE: Diffusion for Hybrid Language Model](https://mlsanity.com/paper/2606.01774/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States](https://mlsanity.com/paper/2605.07579/) (2026)
- [Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models](https://mlsanity.com/paper/2607.28449/) (2026)
- [Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling](https://mlsanity.com/paper/2608.11829/) (2026)
- [Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation](https://mlsanity.com/paper/2609.02998/) (2026)
- [Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models](https://mlsanity.com/paper/2608.01263/) (2026)
- [Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models](https://mlsanity.com/paper/2608.16647/) (2026)
- [Same Model, Different Harness: Different Coding-Agent Results](https://mlsanity.com/paper/2608.26218/) (2026)
- [Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs](https://mlsanity.com/paper/2609.02548/) (2026)
- [Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling](https://mlsanity.com/paper/2604.25578/) (2026)
- [Trust Region Policy Distillation](https://mlsanity.com/paper/2607.04751/) (2026)
- [The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation](https://mlsanity.com/paper/2607.24720/) (2026)
- [Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation](https://mlsanity.com/paper/2609.16937/) (2026)
- [EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing](https://mlsanity.com/paper/2606.00437/) (2026)
- [D3-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation](https://mlsanity.com/paper/2608.24987/) (2026)
- [Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation](https://mlsanity.com/paper/2609.08798/) (2026)

## Abstract (arXiv)

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.