mlsanityData to 7 Oct 2026

Jupiter-N Technical Report

arXiv 2604.17429 ↗First posted 19 Apr 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

We present Jupiter-N, a hybrid reasoning model post-trained from Nemotron 3 Super, a fully open-source 120 billion parameter LLM. We target three objectives: (1) agentic capability via uncertainty-curated trajectories; (2) UK cultural alignment via synthetic data grounded in cultural norms; and (3) Welsh language support via parallel corpora and LLM-translated Welsh conversations. Our data curation strategy carefully preserves the base model's capabilities: using our Forget-Me-Not framework, we mix on-policy synthetic replay with off-policy task data to mitigate catastrophic forgetting, and include a mixture of reasoning and non-reasoning traces to maintain Nemotron's hybrid reasoning ability. Jupiter-N achieves standout gains over Nemotron in Welsh (+18 on ARC-Easy, +5.25 on MMLU-Lite), terminal-use (+9.1 on Terminal Bench 2) and instruction following (+4.4 on IFBench), while retaining the base model capabilities. We frame this work as a reproducible template for sovereign post-training: substituting cultural knowledge, institutional corpora, and target languages produces an equivalent pipeline for any country. All model weights and all post-training datasets are publicly released under open licences.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 15 of its 30 references that are in the map. First posted on arXiv 19 Apr 2026.

Builds on

15 of 30 references.

References · 15

  1. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  2. 2018Experience Replay for Continual Learningcited by 1,074
  3. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  4. 2026Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfacescited by 515
  5. 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrinkcited by 183
  6. 2023Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensionscited by 111
  7. 2024CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologiescited by 98
  8. 2026OpenClaw-RL: Train Any Agent Simply by Talkingcited by 83
  9. 2024Mitigating Catastrophic Forgetting in Language Transfer via Model Mergingcited by 36
  10. 2026On Data Engineering for Scaling LLM Terminal Capabilitiescited by 34
  11. 2024Self-Pluralising Culture Alignment for Large Language Modelscited by 31
  12. 2024Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpuscited by 24
3 more
  1. 2024BgGPT 1.0: Extending English-centric LLMs to other languagescited by 7
  2. 2025Sovereign Large Language Models: Advantages, Strategy and Regulationscited by 1
  3. 2025On Structured State-Space Dualitycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning
  2. 2025LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs
  3. 2025IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation
  4. 2025MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
  5. 2026CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
  6. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debate
  8. 2025Llama-Nemotron: Efficient Reasoning Models