---
title: "Nemotron-Cascade 2 — paper by Yang et al. (2026)"
description: "Post-training a single LLM across many reasoning and agentic domains is hard. 87 references, cited by 16 papers here."
authors: ["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"]
year: 2026
venue: "arXiv:2603.19220"
source: "https://arxiv.org/abs/2603.19220"
doi: "10.48550/arxiv.2603.19220"
arxiv: "2603.19220"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yang-2026-nemotron-cascade-2-post-training/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-nemotron-cascade-2-post-training/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/) / Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

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

**Authors:** [Zhuolin Yang](https://md.research.elamur.ai/free/en/authors/zhuolin-yang/), [Zihan Liu](https://md.research.elamur.ai/free/en/authors/zihan-liu/), [Yang Chen](https://md.research.elamur.ai/free/en/authors/yang-chen/), [Wenliang Dai](https://md.research.elamur.ai/free/en/authors/wenliang-dai/), [Boxin Wang](https://md.research.elamur.ai/free/en/authors/boxin-wang/), [Sheng-Chieh Lin](https://md.research.elamur.ai/free/en/authors/sheng-chieh-lin/), [Chankyu Lee](https://md.research.elamur.ai/free/en/authors/chankyu-lee/), [Yangyi Chen](https://md.research.elamur.ai/free/en/authors/yangyi-chen/), [Dongfu Jiang](https://md.research.elamur.ai/free/en/authors/dongfu-jiang/), Jiafan He, [Renjie Pi](https://md.research.elamur.ai/free/en/authors/renjie-pi/), Grace Lam, [Nayeon Lee](https://md.research.elamur.ai/free/en/authors/nayeon-lee/), Alexander Bukharin, [Mohammad Shoeybi](https://md.research.elamur.ai/free/en/authors/mohammad-shoeybi/), [Bryan Catanzaro](https://md.research.elamur.ai/free/en/authors/bryan-catanzaro/) and [Wei Ping](https://md.research.elamur.ai/free/en/authors/wei-ping/) · **Year:** 2026 · **Venue:** arXiv:2603.19220 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2603.19220) · [PDF](https://arxiv.org/pdf/2603.19220) · [DOI 10.48550/arxiv.2603.19220](https://doi.org/10.48550/arxiv.2603.19220) · [arXiv 2603.19220](https://arxiv.org/abs/2603.19220) · [OpenAlex](https://openalex.org/W7139913273)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 16 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Post-training a single LLM across many reasoning and agentic domains is hard. Mixing diverse RL environments can destabilize training, and gains in one area often erode others. Nemotron-Cascade 2 extends NVIDIA's earlier Cascade RL approach, which trains domain by domain in sequence, to address this. The base model is Nemotron-3-Nano-30B-A3B-Base, a Mixture-of-Experts with 30B total and 3B active parameters. The pipeline starts with SFT on a carefully curated dataset spanning many domains. It then runs a longer chain of RL stages. Tasks with similar output formats and verification costs are grouped into joint multi-domain RL. The key new element is multi-domain on-policy distillation (MOPD). Here the best intermediate checkpoint for each domain serves as a teacher, which lets the model recover scores that slipped in later stages. The resulting model reaches gold-medal-level results on IMO 2025, IOI 2025 and the ICPC World Finals. It also performs strongly on alignment, long-context and agentic benchmarks. This suggests small open models can achieve very high capability per parameter.

## Key points
- Nemotron-Cascade-2-30B-A3B is described as only the second open-weight model, after DeepSeek-V3.2-Speciale-671B-A37B, to reach gold-medal level at IMO, IOI and ICPC 2025. It does so with about 20× fewer parameters.
- The RL cascade includes these stages: IF-RL, multi-domain RL, MOPD, RLHF, long-context RL, code RL and SWE RL. The SWE RL stage covers both agentless and execution-based agentic scaffold training.
- The SFT data covers math, code, science, long context, chat, instruction following, safety, and conversational, SWE and terminal agents.
- The model supports a context window of up to 1M tokens. A former IMO gold medalist manually graded its IMO 2025 proofs.
- Released resources include the model checkpoint, Nemotron-Cascade-2-SFT-Data and Nemotron-Cascade-2-RL-Data.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 242 works

## Cite

Cite as: 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 and Wei Ping. 2026. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation. arXiv:2603.19220.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{yang2026nemotron,
  title = {{Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation}},
  author = {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 and Wei Ping},
  year = {2026},
  doi = {10.48550/arxiv.2603.19220},
  eprint = {2603.19220},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2603.19220}
}
```

- [← previous MMSearch-R1: Incentivizing LMMs to Search](https://md.research.elamur.ai/free/en/papers/wu-2026-mmsearch-r1-incentivizing-lmms-search/)
- [next → New Trends for Modern Machine Translation with Large Reasoning Models](https://md.research.elamur.ai/free/en/papers/liu-2026-new-trends-modern-machine-translation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/)

## References

87 references, 39 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Gretel synthetic safety alignment dataset, 12 2024. URL [https://huggingface.co/datasets/](https://huggingface.co/datasets/) gretelai/gretel-safety-alignment-en-v1. 9 [↗](https://huggingface.co/datasets/)
2. Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos Garea, Matthieu Geist, and Olivier Bachem. [On-policy distillation of language models: Learning from self-generated mistakes](https://md.research.elamur.ai/free/en/papers/agarwal-2023-policy-distillation-language-models-learning/). In The twelfth international conference on learning representations, 2024. 12
3. Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K Arora, Yu Bai, Bowen Baker, Haiming Bao, et al. [gpt-oss-120b & gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). arXiv preprint arXiv:2508.10925, 2025. 7, 8, 9, 20
4. Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek, Siddhartha Jain, Jocelyn Huang, Vahid Noroozi, and Boris Ginsburg. [Opencodereasoning: Advancing data distillation for competitive coding](https://md.research.elamur.ai/free/en/papers/ahmad-2025-opencodereasoning-advancing-data-distillation-competitive/). arXiv preprint arXiv:2504.01943, 2025. 7
5. Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Andrei Andriushchenko, Maria Trofimova, Daria Litvintseva, and Boris Yangel. Swe-rebench: An automated pipeline for task collection and decontaminated evaluation of software engineering agents. arXiv preprint… — [arXiv:2505.20411](https://arxiv.org/abs/2505.20411) [find](https://scholar.google.com/scholar?q=Ibragim+Badertdinov%2C+Alexander+Golubev%2C+Maksim+Nekrashevich%2C+Anton+Shevtsov%2C+Simon+Karasik%2C+Andrei+Andriushchenko%2C+Maria+Trofimova%2C+Daria+Litvintseva%2C+and+Boris+Yangel%2E+Swe%2Drebench%3A+An+automated+pipel)
6. Yushi Bai, Shangqing Tu, Jiajie Zhang, Hao Peng, Xiaozhi Wang, Xin Lv, Shulin Cao, Jiazheng Xu, Lei Hou, Yuxiao Dong, et al. [Longbench v2: Towards deeper understanding and reasoning on realistic long-context multitasks](https://md.research.elamur.ai/free/en/papers/bai-2024-longbench-v2-deeper-understanding/). In Proceedings of the 63rd Annual Meeting of the Association for Computational L…
7. Victor Barres, Honghua Dong, Soham Ray, Xujie Si, and Karthik Narasimhan. 𝜏 2 -bench: Evaluating conversational agents in a dual-control environment, 2025. URL https://arxiv.org/abs/2506. 07982. 23 [↗](https://arxiv.org/abs/2506)
8. Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, Aditya Vavre, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, et al. [Nemotron 3 nano: Open, efficient mixture-of-experts hybrid mamba-transformer model for agentic reasoning](https://md.research.elamur.ai/free/en/papers/blakeman-2025-nemotron-3-nano-open-efficient/). arXiv preprint arXiv…
9. Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, Aditya Vavre, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, et al. Nvidia nemotron 3: Efficient and open intelligence. arXiv preprint arXiv:2512.20856, 2025. 5, 9 — [arXiv:2512.20856](https://arxiv.org/abs/2512.20856) [find](https://scholar.google.com/scholar?q=Aaron+Blakeman%2C+Aaron+Grattafiori%2C+Aarti+Basant%2C+Abhibha+Gupta%2C+Abhinav+Khattar%2C+Adi+Renduchintala%2C+Aditya+Vavre%2C+Akanksha+Shukla%2C+Akhiad+Bercovich%2C+Aleksander+Ficek%2C+et+al%2E+Nvidia+nemotron+3%3A+Efficie)
10. Yang Chen, Zhuolin Yang, Zihan Liu, Chankyu Lee, Peng Xu, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. Acereason-nemotron: Advancing math and code reasoning through reinforcement learning. Advances in neural information processing systems, 2025. 13 [find](https://scholar.google.com/scholar?q=Yang+Chen%2C+Zhuolin+Yang%2C+Zihan+Liu%2C+Chankyu+Lee%2C+Peng+Xu%2C+Mohammad+Shoeybi%2C+Bryan+Catanzaro%2C+and+Wei+Ping%2E+Acereason%2Dnemotron%3A+Advancing+math+and+code+reasoning+through+reinforcement+learning%2E+Advance)
11. Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E. Gonzalez, and Ion Stoica. [Chatbot arena: An open platform for evaluating llms by human preference](https://md.research.elamur.ai/free/en/papers/chiang-2024-chatbot-arena-open-platform-evaluating/), 2024. 14
12. Kaustubh Deshpande, Ved Sirdeshmukh, Johannes Baptist Mols, Lifeng Jin, Ed-Yeremai Hernandez-Cardona, Dean Lee, Jeremy Kritz, Willow E Primack, Summer Yue, and Chen Xing. Multichallenge: A realistic multi-turn conversation evaluation benchmark challenging to frontier llms. In Findings of the Associa… [find](https://scholar.google.com/scholar?q=Kaustubh+Deshpande%2C+Ved+Sirdeshmukh%2C+Johannes+Baptist+Mols%2C+Lifeng+Jin%2C+Ed%2DYeremai+Hernandez%2DCardona%2C+Dean+Lee%2C+Jeremy+Kritz%2C+Willow+E+Primack%2C+Summer+Yue%2C+and+Chen+Xing%2E+Multichallenge%3A+A+realistic+m)
13. Daniel Deutsch, Eleftheria Briakou, Isaac Rayburn Caswell, Mara Finkelstein, Rebecca Galor, Juraj Juraska, Geza Kovacs, Alison Lui, Ricardo Rei, Jason Riesa, et al. [Wmt24++: Expanding the language coverage of wmt24 to 55 languages & dialects](https://md.research.elamur.ai/free/en/papers/deutsch-2025-wmt24-expanding-language-coverage-wmt24/). In Findings of the Association for Computational Linguist…
14. Shihan Dou, Ming Zhang, Zhangyue Yin, Chenhao Huang, Yujiong Shen, Junzhe Wang, Jiayi Chen, Yuchen Ni, Junjie Ye, Cheng Zhang, et al. Cl-bench: A benchmark for context learning. arXiv preprint arXiv:2602.03587, 2026. 23 — [arXiv:2602.03587](https://arxiv.org/abs/2602.03587) [find](https://scholar.google.com/scholar?q=Shihan+Dou%2C+Ming+Zhang%2C+Zhangyue+Yin%2C+Chenhao+Huang%2C+Yujiong+Shen%2C+Junzhe+Wang%2C+Jiayi+Chen%2C+Yuchen+Ni%2C+Junjie+Ye%2C+Cheng+Zhang%2C+et+al%2E+Cl%2Dbench%3A+A+benchmark+for+context+learning%2E+arXiv+preprint+arXiv%3A2)
15. Wei Du, Shubham Toshniwal, Branislav Kisacanin, Sadegh Mahdavi, Ivan Moshkov, George Armstrong, Stephen Ge, Edgar Minasyan, Feng Chen, and Igor Gitman. Nemotron-math: Efficient long-context distillation of mathematical reasoning from multi-mode supervision. arXiv preprint arXiv:2512.15489, 2025. 7 [find](https://scholar.google.com/scholar?q=Wei+Du%2C+Shubham+Toshniwal%2C+Branislav+Kisacanin%2C+Sadegh+Mahdavi%2C+Ivan+Moshkov%2C+George+Armstrong%2C+Stephen+Ge%2C+Edgar+Minasyan%2C+Feng+Chen%2C+and+Igor+Gitman%2E+Nemotron%2Dmath%3A+Efficient+long%2Dcontext+distillati)
16. Tony Feng, Trieu H. Trinh, Garrett Bingham, Dawsen Hwang, Yuri Chervonyi, Junehyuk Jung, Joonkyung Lee, Carlo Pagano, Sang-hyun Kim, Federico Pasqualotto, Sergei Gukov, Jonathan N. Lee, Junsu Kim, Kaiying Hou, Golnaz Ghiasi, Yi Tay, YaGuang Li, Chenkai Kuang, Yuan Liu, Hanzhao Lin, Evan Zheran Liu,… [find](https://scholar.google.com/scholar?q=Tony+Feng%2C+Trieu+H%2E+Trinh%2C+Garrett+Bingham%2C+Dawsen+Hwang%2C+Yuri+Chervonyi%2C+Junehyuk+Jung%2C+Joonkyung+Lee%2C+Carlo+Pagano%2C+Sang%2Dhyun+Kim%2C+Federico+Pasqualotto%2C+Sergei+Gukov%2C+Jonathan+N%2E+Lee%2C+Junsu+Kim%2C+Kai)
17. Aryo Pradipta Gema, Joshua Ong Jun Leang, Giwon Hong, Alessio Devoto, Alberto Carlo Maria Mancino, Rohit Saxena, Xuanli He, Yu Zhao, Xiaotang Du, Mohammad Reza Ghasemi Madani, Claire Barale, Robert McHardy, Joshua Harris, Jean Kaddour, Emile van Krieken, and Pasquale Minervini. Are we done with mmlu… [find](https://scholar.google.com/scholar?q=Aryo+Pradipta+Gema%2C+Joshua+Ong+Jun+Leang%2C+Giwon+Hong%2C+Alessio+Devoto%2C+Alberto+Carlo+Maria+Mancino%2C+Rohit+Saxena%2C+Xuanli+He%2C+Yu+Zhao%2C+Xiaotang+Du%2C+Mohammad+Reza+Ghasemi+Madani%2C+Claire+Barale%2C+Robert+Mc)
18. Gemini Team. products-and-platforms/products/gemini/gemini-3/, 2025. Google Blog, November 18, 2025. 17 [find](https://scholar.google.com/scholar?q=Gemini+Team%2E+products%2Dand%2Dplatforms%2Fproducts%2Fgemini%2Fgemini%2D3%2F%2C+2025%2E+Google+Blog%2C+November+18%2C+2025%2E+17)
19. Gemini Team. Advanced version of gemini with deep think officially achieves gold-medal standard at the international mathematical olympiad. [https://deepmind.google/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/](https://deepmind.google/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/), 202… [↗](https://deepmind.google/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/)
20. Gemini Team. Gemini 3 deep think: Advancing science, research and engineering. [https://blog.google/innovation-and-ai/models-and-research/gemini-models/](https://blog.google/innovation-and-ai/models-and-research/gemini-models/) gemini-3-deep-think/, 2026. Google Blog, February 12, 2026. 17 [↗](https://blog.google/innovation-and-ai/models-and-research/gemini-models/)
21. Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar, Aishwarya Padmakumar, Traian Rebedea, Jibin Rajan Varghese, and Christopher Parisien. Aegis2. 0: A diverse ai safety dataset and risks taxonomy for alignment of llm guardrails. In Proceedings of the 2025 [Conference of the Nations of the Amer…](https://md.research.elamur.ai/free/en/papers/ghosh-2025-aegis2-0-diverse-ai-safety/)
22. Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. [Minillm: On-policy distillation of large language models](https://md.research.elamur.ai/free/en/papers/gu-2023-minillm-policy-distillation-large-language/). In ICLR, 2024. 12
23. Nuno M Guerreiro, Ricardo Rei, Daan van Stigt, Luisa Coheur, Pierre Colombo, and André FT Martins. [xcomet: Transparent machine translation evaluation through fine-grained error detection](https://md.research.elamur.ai/free/en/papers/guerreiro-2024-xcomet-transparent-machine-translation-evaluation/). Transactions of the Association for Computational Linguistics, 12:979–995, 2024. 24
24. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. [Deepseek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948, 2025. 4
25. Adib Hasan, Ileana Rugina, and Alex Wang. Pruning for protection: Increasing jailbreak resistance in aligned llms without fine-tuning. In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 417–430, 2024. 9 [find](https://scholar.google.com/scholar?q=Adib+Hasan%2C+Ileana+Rugina%2C+and+Alex+Wang%2E+Pruning+for+protection%3A+Increasing+jailbreak+resistance+in+aligned+llms+without+fine%2Dtuning%2E+In+Proceedings+of+the+7th+BlackboxNLP+Workshop%3A+Analyzing+and+Int)
26. Zhongmou He, Yee Man Choi, Kexun Zhang, Jiabao Ji, Junting Zhou, Dejia Xu, Ivan Bercovich, Aidan Zhang, and Lei Li. Hardtests: Synthesizing high-quality test cases for llm coding. arXiv preprint arXiv:2505.24098, 2025. 7 — [arXiv:2505.24098](https://arxiv.org/abs/2505.24098) [find](https://scholar.google.com/scholar?q=Zhongmou+He%2C+Yee+Man+Choi%2C+Kexun+Zhang%2C+Jiabao+Ji%2C+Junting+Zhou%2C+Dejia+Xu%2C+Ivan+Bercovich%2C+Aidan+Zhang%2C+and+Lei+Li%2E+Hardtests%3A+Synthesizing+high%2Dquality+test+cases+for+llm+coding%2E+arXiv+preprint+arXiv)
27. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). arXiv preprint arXiv:2009.03300, 2020. 21
28. HMMT. Harvard-mit mathematics tournament february 2025, 2025. 20 [find](https://scholar.google.com/scholar?q=HMMT%2E+Harvard%2Dmit+mathematics+tournament+february+2025%2C+2025%2E+20)
29. Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman, Shantanu Acharya, Dima Rekesh, Fei Jia, Yang Zhang, and Boris Ginsburg. Ruler: What’s the real context size of your long-context language models? arXiv preprint arXiv:2404.[06654, 2024](https://md.research.elamur.ai/free/en/papers/hsieh-2024-ruler-s-real-context-size/). 22
30. Siming Huang, Tianhao Cheng, Jason Klein Liu, Jiaran Hao, Liuyihan Song, Yang Xu, J Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, et al. [Opencoder: The open cookbook for top-tier code large language models](https://md.research.elamur.ai/free/en/papers/huang-2025-opencoder-open-cookbook-top-tier/). arXiv preprint arXiv:2411.04905, 2024. 7
31. IMO. International Mathematical Olympiad, 2025. 20 [find](https://scholar.google.com/scholar?q=IMO%2E+International+Mathematical+Olympiad%2C+2025%2E+20)
32. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. [Livecodebench: Holistic and contamination free evaluation of large language models for code](https://md.research.elamur.ai/free/en/papers/jain-2024-livecodebench-holistic-contamination-free-evaluation/). arXiv preprint arXiv:2403.07974, 2024. 19, 21
33. Naman Jain, Jaskirat Singh, Manish Shetty, Liang Zheng, Koushik Sen, and Ion Stoica. R2e-gym: Procedural environments and hybrid verifiers for scaling open-weights swe agents, 2025. URL https://arxiv.org/abs/2504.07164. 9, 16 — [arXiv:2504.07164](https://arxiv.org/abs/2504.07164) [↗](https://arxiv.org/abs/2504.07164)
34. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. [Swe-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) arXiv preprint arXiv:2310.06770, 2023. 23
35. Gregory Kamradt. Needle in a haystack - pressure testing llms. Github, 2023. URL [https://github.com/gkamradt/LLMTest_NeedleInAHaystack/tree/main](https://github.com/gkamradt/LLMTest_NeedleInAHaystack/tree/main). 22 [↗](https://github.com/gkamradt/LLMTest_NeedleInAHaystack/tree/main)
36. Diederik P Kingma. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). arXiv preprint arXiv:1412.6980, 2014. 12, 15
37. Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu, Banghua Zhu, Joseph E Gonzalez, and Ion Stoica. [From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline](https://md.research.elamur.ai/free/en/papers/li-2024-crowdsourced-data-high-quality-benchmarks/). arXiv preprint arXiv:2406.11939, 2024. 14, 22
38. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. Deepseek-V3 technical report. arXiv preprint arXiv:2412.19437, 2024. 8 [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+et+al%2E+Deepseek%2DV3+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E19437%2C+2024%2E)
39. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, et al. Deepseek-v3. 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.[02556, 2025](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/). 4, 6, 7, 9
40. Zihan Liu, Yang Chen, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. AceMath: Advancing frontier math reasoning with post-training and reward modeling. ACL, 2024. 20 [find](https://scholar.google.com/scholar?q=Zihan+Liu%2C+Yang+Chen%2C+Mohammad+Shoeybi%2C+Bryan+Catanzaro%2C+and+Wei+Ping%2E+AceMath%3A+Advancing+frontier+math+reasoning+with+post%2Dtraining+and+reward+modeling%2E+ACL%2C+2024%2E+20)
41. Zihan Liu, Zhuolin Yang, Yang Chen, Chankyu Lee, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. [Acereason-nemotron 1.1: Advancing math and code reasoning through sft and rl synergy](https://md.research.elamur.ai/free/en/papers/liu-2025-acereason-nemotron-1-1-advancing/). ICLR, 2026. 20
42. LM-Provers, Yuxiao Qu, Amrith Setlur, Jasper Dekoninck, Edward Beeching, Jia Li, Ian Wu, Lewis Tunstall, and Aviral Kumar. Qed-nano: Teaching a tiny model to prove hard theorems. [https://huggingface.co/spaces/lm-provers/qed-nano-blogpost](https://huggingface.co/spaces/lm-provers/qed-nano-blogpost), 2026. Blog post. 17 [↗](https://huggingface.co/spaces/lm-provers/qed-nano-blogpost)
43. Kevin Lu and Thinking Machines Lab. On-policy distillation. Thinking Machines Lab: Connectionism, 2025. doi: 10.64434/tml.20251026. [https://thinkingmachines.ai/blog/on-policy-distillation](https://thinkingmachines.ai/blog/on-policy-distillation). 12 — [doi:10.64434/tml.20251026](https://doi.org/10.64434/tml.20251026) [↗](https://thinkingmachines.ai/blog/on-policy-distillation)
44. Weidi Luo, Siyuan Ma, Xiaogeng Liu, Xiaoyu Guo, and Chaowei Xiao. Jailbreakv: A benchmark for assessing the robustness of multimodal large language models against jailbreak attacks. arXiv preprint arXiv:2404.03027, 2024. 9 [find](https://scholar.google.com/scholar?q=Weidi+Luo%2C+Siyuan+Ma%2C+Xiaogeng+Liu%2C+Xiaoyu+Guo%2C+and+Chaowei+Xiao%2E+Jailbreakv%3A+A+benchmark+for+assessing+the+robustness+of+multimodal+large+language+models+against+jailbreak+attacks%2E+arXiv+preprint+arX)
45. Minh-Thang Luong, Dawsen Hwang, Hoang H Nguyen, Golnaz Ghiasi, Yuri Chervonyi, Insuk Seo, Junsu Kim, Garrett Bingham, Jonathan Lee, Swaroop Mishra, et al. [Towards robust mathematical reasoning](https://md.research.elamur.ai/free/en/papers/luong-2025-robust-mathematical-reasoning/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 35406– 35…
46. Wenjie Ma, Andrei Cojocaru, Neel Kolhe, Bradley Louie, Robin Said Sharif, Haihan Zhang, Vincent Zhuang, Matei Zaharia, and Sewon Min. Reliable fine-grained evaluation of natural language math proofs. arXiv preprint arXiv:2510.13888, 2025. 6, 38 — [arXiv:2510.13888](https://arxiv.org/abs/2510.13888) [find](https://scholar.google.com/scholar?q=Wenjie+Ma%2C+Andrei+Cojocaru%2C+Neel+Kolhe%2C+Bradley+Louie%2C+Robin+Said+Sharif%2C+Haihan+Zhang%2C+Vincent+Zhuang%2C+Matei+Zaharia%2C+and+Sewon+Min%2E+Reliable+fine%2Dgrained+evaluation+of+natural+language+math+proofs%2E+)
47. MAA. American Invitational Mathematics Examination - AIME 2025, 2025. 20 [find](https://scholar.google.com/scholar?q=MAA%2E+American+Invitational+Mathematics+Examination+%2D+AIME+2025%2C+2025%2E+20)
48. MAA. American Invitational Mathematics Examination - AIME 2026, 2026. 20 [find](https://scholar.google.com/scholar?q=MAA%2E+American+Invitational+Mathematics+Examination+%2D+AIME+2026%2C+2026%2E+20)
49. Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini, Boxuan Li, Harsh Raj, Ivan Bercovich, Lin Shi, Jeong Yeon Shin, Thomas Walshe, E. Kelly Buchanan, Junhong Shen, Guanghao Ye, Haowei Lin, Jason Poulos, Maoyu Wang, Marianna Nezhurina, Jenia Jitsev, Di Lu, Orfeas Menis Mastromichalakis, Zhiwei Xu,… — [arXiv:2601.11868](https://arxiv.org/abs/2601.11868) [find](https://scholar.google.com/scholar?q=Mike+A%2E+Merrill%2C+Alexander+G%2E+Shaw%2C+Nicholas+Carlini%2C+Boxuan+Li%2C+Harsh+Raj%2C+Ivan+Bercovich%2C+Lin+Shi%2C+Jeong+Yeon+Shin%2C+Thomas+Walshe%2C+E%2E+Kelly+Buchanan%2C+Junhong+Shen%2C+Guanghao+Ye%2C+Haowei+Lin%2C+Jason+Pou)
50. NVIDIA. Nemo gym: An open source library for scaling reinforcement learning environments for llm. [https://github.com/NVIDIA-NeMo/Gym](https://github.com/NVIDIA-NeMo/Gym), 2025. GitHub repository. 15 [↗](https://github.com/NVIDIA-NeMo/Gym)
51. NVIDIA. NeMo RL: A Scalable and Efficient Post-Training Library. NVIDIA-NeMo/RL, 2025. GitHub repository. 11 [https://github.com/](https://github.com/) [↗](https://github.com/)
52. NVIDIA. NeMo-Skills. [https://github.com/NVIDIA-NeMo/Skills](https://github.com/NVIDIA-NeMo/Skills), 2025. GitHub repository. 20 [↗](https://github.com/NVIDIA-NeMo/Skills)
53. NVIIDA. Nemotron-3-Nano-30B-A3B-Base-BF16, 2025. URL [https://huggingface.co/nvidia/](https://huggingface.co/nvidia/) NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16. 6 [↗](https://huggingface.co/nvidia/)
54. OpenAI. Introducing SWE-bench Verified, 2024. 23 [find](https://scholar.google.com/scholar?q=OpenAI%2E+Introducing+SWE%2Dbench+Verified%2C+2024%2E+23)
55. OpenAI. Introducing GPT-5, 2025. 17 [find](https://scholar.google.com/scholar?q=OpenAI%2E+Introducing+GPT%2D5%2C+2025%2E+17)
56. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). NeurIPS, 35, 2022. 4
57. Jiayi Pan*, Xingyao Wang*, Graham Neubig, Navdeep Jaitly, Heng Ji, Alane Suhr, and Yizhe Zhang. Training software engineering agents and verifiers with swe-gym. In ICML, 2025. URL https://arxiv.org/abs/2412.21139. 9, 16 [↗](https://arxiv.org/abs/2412.21139)
58. Shishir G. Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E. Gonzalez. The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models. In ICML, 2025. 23 [find](https://scholar.google.com/scholar?q=Shishir+G%2E+Patil%2C+Huanzhi+Mao%2C+Charlie+Cheng%2DJie+Ji%2C+Fanjia+Yan%2C+Vishnu+Suresh%2C+Ion+Stoica%2C+and+Joseph+E%2E+Gonzalez%2E+The+Berkeley+Function+Calling+Leaderboard+%28BFCL%29%3A+From+Tool+Use+to+Agentic+Evaluatio)
59. Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, and et al. Humanity’s last exam, 2025. [URL https://arxiv.org/abs/2501.14249](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/). 21 [↗](https://arxiv.org/abs/2501.14249)
60. Renjie Pi, Grace Lam, Mohammad Shoeybi, Pooya Jannaty, Bryan Catanzaro, and Wei Ping. On data engineering for scaling llm terminal capabilities, 2026. URL https://arxiv.org/abs/2602.21193. 9 — [arXiv:2602.21193](https://arxiv.org/abs/2602.21193) [↗](https://arxiv.org/abs/2602.21193)
61. Valentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert, and Hannaneh Hajishirzi. [Generalizing verifiable instruction following](https://md.research.elamur.ai/free/en/papers/pyatkin-2025-generalizing-verifiable-instruction-following/), 2025. URL [https://huggingface.co/datasets/allenai/IF_multi_constraints_upto5](https://huggingface.co/datasets/allenai/IF_multi_constraints_upto5). 11, 12, 22 [↗](https://huggingface.co/datasets/allenai/IF_multi_constraints_upto5)
62. Qwen Team. Qwen3.5: Towards native multimodal agents, February 2026. URL [https://qwen.ai/](https://qwen.ai/) blog?id=qwen3.5. 5 [↗](https://qwen.ai/)
63. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. [Gpqa: A graduate-level google-proof q&a benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling, 2024. 21
64. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al. [DeepseekMath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300, 2024. 11
65. Zhihong Shao, Yuxiang Luo, Chengda Lu, ZZ Ren, Jiewen Hu, Tian Ye, Zhibin Gou, Shirong Ma, and Xiaokang Zhang. [Deepseekmath-v2: Towards self-verifiable mathematical reasoning](https://md.research.elamur.ai/free/en/papers/shao-2025-deepseekmath-v2-self-verifiable/). arXiv preprint arXiv:2511.22570, 2025. 17
66. Atefeh Sohrabizadeh, Jialin Song, Mingjie Liu, Rajarshi Roy, Chankyu Lee, Jonathan Raiman, and Bryan Catanzaro. Nemotron-cortexa: Enhancing llm agents for software engineering tasks via improved localization and solution diversity. In Forty-second International Conference on Machine Learning, 2025.… [find](https://scholar.google.com/scholar?q=Atefeh+Sohrabizadeh%2C+Jialin+Song%2C+Mingjie+Liu%2C+Rajarshi+Roy%2C+Chankyu+Lee%2C+Jonathan+Raiman%2C+and+Bryan+Catanzaro%2E+Nemotron%2Dcortexa%3A+Enhancing+llm+agents+for+software+engineering+tasks+via+improved+local)
67. Artificial Analysis Team. Artificial analysis long context reasoning benchmark(lcr), 2025. 22 [find](https://scholar.google.com/scholar?q=Artificial+Analysis+Team%2E+Artificial+analysis+long+context+reasoning+benchmark%28lcr%29%2C+2025%2E+22)
68. Minyang Tian, Luyu Gao, Shizhuo D Zhang, Xinan Chen, Cunwei Fan, Xuefei Guo, Roland Haas, Pan Ji, Kittithat Krongchon, Yao Li, et al. Scicode: A research coding benchmark curated by scientists. Advances in Neural Information Processing Systems, 37:30624–30650, 2024. 21 [find](https://scholar.google.com/scholar?q=Minyang+Tian%2C+Luyu+Gao%2C+Shizhuo+D+Zhang%2C+Xinan+Chen%2C+Cunwei+Fan%2C+Xuefei+Guo%2C+Roland+Haas%2C+Pan+Ji%2C+Kittithat+Krongchon%2C+Yao+Li%2C+et+al%2E+Scicode%3A+A+research+coding+benchmark+curated+by+scientists%2E+Advanc)
69. Boxin Wang, Chankyu Lee, Nayeon Lee, Sheng-Chieh Lin, Wenliang Dai, Yang Chen, Yangyi Chen, Zhuolin Yang, Zihan Liu, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. Nemotron-Cascade: Scaling cascaded reinforcement learning for general-purpose reasoning models. arXiv preprint arXiv:2512.13607, 2025.… — [arXiv:2512.13607](https://arxiv.org/abs/2512.13607) [find](https://scholar.google.com/scholar?q=Boxin+Wang%2C+Chankyu+Lee%2C+Nayeon+Lee%2C+Sheng%2DChieh+Lin%2C+Wenliang+Dai%2C+Yang+Chen%2C+Yangyi+Chen%2C+Zhuolin+Yang%2C+Zihan+Liu%2C+Mohammad+Shoeybi%2C+Bryan+Catanzaro%2C+and+Wei+Ping%2E+Nemotron%2DCascade%3A+Scaling+cascaded)
70. Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, a… — [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://md.research.elamur.ai/free/en/papers/wang-2024-openhands-open-platform-ai/)
71. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, et al. [Mmlu-pro: A more robust and challenging multi-task language understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/). arXiv preprint arXiv:2406.01574, 2024. 21
72. Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Hoo-Chang Shin, Felipe Soares, Alexander Bukharin, Ellie Evans, Yi Dong, and Oleksii Kuchaiev. Helpsteer3-preference: Open human-annotated preference data across diverse tasks and languages, 2025. URL https://arxiv.org/abs/2505.11475. 14 — [arXiv:2505.11475](https://arxiv.org/abs/2505.11475) [↗](https://arxiv.org/abs/2505.11475)
73. Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Hoo-Chang Shin, Felipe Soares, Alexander Bukharin, Ellie Evans, Yi Dong, and Oleksii Kuchaiev. Helpsteer3-preference: Open human-annotated preference data across diverse tasks and languages, 2025. URL https://arxiv.org/abs/2505.11475. 14 — [arXiv:2505.11475](https://arxiv.org/abs/2505.11475) [↗](https://arxiv.org/abs/2505.11475)
74. Yuxiang Wei, Olivier Duchenne, Jade Copet, Quentin Carbonneaux, Lingming Zhang, Daniel Fried, Gabriel Synnaeve, Rishabh Singh, and Sida I Wang. Swe-rl: Advancing llm reasoning via reinforcement learning on open software evolution. arXiv preprint arXiv:2502.18449, 2025. 9 [find](https://scholar.google.com/scholar?q=Yuxiang+Wei%2C+Olivier+Duchenne%2C+Jade+Copet%2C+Quentin+Carbonneaux%2C+Lingming+Zhang%2C+Daniel+Fried%2C+Gabriel+Synnaeve%2C+Rishabh+Singh%2C+and+Sida+I+Wang%2E+Swe%2Drl%3A+Advancing+llm+reasoning+via+reinforcement+learni)
75. Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8:229–256, 1992. 11 [find](https://scholar.google.com/scholar?q=Ronald+J+Williams%2E+Simple+statistical+gradient%2Dfollowing+algorithms+for+connectionist+reinforcement+learning%2E+Machine+learning%2C+8%3A229%E2%80%93256%2C+1992%2E+11)
76. Bangjun Xiao, Bingquan Xia, Bo Yang, Bofei Gao, Bowen Shen, Chen Zhang, Chenhong He, Chiheng Lou, Fuli Luo, Gang Wang, et al. [Mimo-v2-flash technical report](https://md.research.elamur.ai/free/en/papers/team-2026-llm-mimo-v2-flash-technical/). arXiv preprint arXiv:2601.02780, 2026. 4, 12
77. Peng Xu, Wei Ping, Xianchao Wu, Chejian Xu, Zihan Liu, Mohammad Shoeybi, and Bryan Catanzaro. Chatqa 2: Bridging the gap to proprietary llms in long context and rag capabilities. arXiv preprint arXiv:2407.14482, 2024. 8 — [arXiv:2407.14482](https://arxiv.org/abs/2407.14482) [find](https://scholar.google.com/scholar?q=Peng+Xu%2C+Wei+Ping%2C+Xianchao+Wu%2C+Chejian+Xu%2C+Zihan+Liu%2C+Mohammad+Shoeybi%2C+and+Bryan+Catanzaro%2E+Chatqa+2%3A+Bridging+the+gap+to+proprietary+llms+in+long+context+and+rag+capabilities%2E+arXiv+preprint+arXiv%3A)
78. Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, et al. [Mmlu-prox: A multilingual benchmark for advanced large language model evaluation](https://md.research.elamur.ai/free/en/papers/xuan-2025-mmlu-prox-multilingual-benchmark-advanced/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pag…
79. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388, 2025. 8, 9, 12, 14
80. John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. [Swe-agent: Agent-computer interfaces enable automated software engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/). In A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang, editors, Advances in Neural…
81. Zonghan Yang, Shengjie Wang, Kelin Fu, Wenyang He, Weimin Xiong, Yibo Liu, Yibo Miao, Bofei Gao, Yejie Wang, YINGWEI MA, Yanhao Li, Yue Liu, Zhenxing Hu, kaitai zhang, Shuyi Wang, Huarong Chen, Flood Sung, Yang Liu, Yang Gao, Zhilin Yang, and Tianyu Liu. Kimi-dev: Agentless training as skill prior f… — [Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents](https://md.research.elamur.ai/free/en/papers/yang-2025-kimi-dev-agentless-training/)
82. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, Tiantian Fan, Gaohong Liu, Lingjun Liu, et al. [DAPO: An open-source LLM reinforcement learning system at scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/). arXiv preprint arXiv:2503.14476, 2025. 11
83. Aohan Zeng, Xin Lv, Zhenyu Hou, Zhengxiao Du, Qinkai Zheng, Bin Chen, Da Yin, Chendi Ge, Chengxing Xie, Cunxiang Wang, et al. [Glm-5: from vibe coding to agentic engineering](https://md.research.elamur.ai/free/en/papers/team-2026-5-glm-5-vibe-coding/). arXiv preprint arXiv:2602.15763, 2026. 4, 12
84. Wenting Zhao, Xiang Ren, Jack Hessel, Claire Cardie, Yejin Choi, and Yuntian Deng. [Wildchat: 1m chatgpt interaction logs in the wild](https://md.research.elamur.ai/free/en/papers/zhao-2024-wildchat-1m-chatgpt-interaction-logs/). arXiv preprint arXiv:2405.01470, 2024. 8
85. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Tianle Li, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zhuohan Li, Zi Lin, Eric. P Xing, Joseph E. Gonzalez, Ion Stoica, and Hao Zhang. [Lmsys-chat-1m: A large-scale real-world llm conversation dataset](https://md.research.elamur.ai/free/en/papers/zheng-2023-lmsys-chat-1m-large-scale/), 2023. 8
86. Zihan Zheng, Zerui Cheng, Zeyu Shen, Shang Zhou, Kaiyuan Liu, Hansen He, Dongruixuan Li, Stanley Wei, Hangyi Hao, Jianzhu Yao, et al. Livecodebench pro: How do olympiad medalists judge llms in competitive programming? arXiv preprint arXiv:2506.11928, 2025. 19, 21, 27 — [arXiv:2506.11928](https://arxiv.org/abs/2506.11928) [find](https://scholar.google.com/scholar?q=Zihan+Zheng%2C+Zerui+Cheng%2C+Zeyu+Shen%2C+Shang+Zhou%2C+Kaiyuan+Liu%2C+Hansen+He%2C+Dongruixuan+Li%2C+Stanley+Wei%2C+Hangyi+Hao%2C+Jianzhu+Yao%2C+et+al%2E+Livecodebench+pro%3A+How+do+olympiad+medalists+judge+llms+in+competi)
87. Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, and Le Hou. [Instruction-following evaluation for large language models](https://md.research.elamur.ai/free/en/papers/zhou-2023-instruction-following-evaluation-large-language/), 2023. URL [https://arxiv.org/](https://arxiv.org/) abs/2311.07911. 22 [↗](https://arxiv.org/)

*Updated 30 October 2026*