OSU NLP group releases QUEST, an open-source deep research agent framework with models ranging from 2B to 35B parameters

VIEWS339LIKES4

@ysu_nlp @furongh Nb!

Yu Su@ysu_nlp

We trained a ~frontier Deep Research Agent on academic budget

> 32 H100s > 8K synthetic samples > fully open training infra + recipe (SFT, mid-training, RL) > models of diff sizes (2B -> 35B) ready to use out of the box

This is yet another demonstration of how the frontier of AI is changing. We have reached a point where open models + a small capable team + a few hundred Ks can produce specialized models with ~frontier capabilities. The future of AI doesn’t have to be held in a chokehold by a handful of closed models.

We've open-sourced everything we've built and learned from this project. Hope it helps the community build more!

📌 Project: https://osu-nlp-group.github.io/QUEST 📌 Paper: https://arxiv.org/abs/2605.24218 📌 Code: https://github.com/OSU-NLP-Group/QUEST 📌 Model Weights and Data: https://huggingface.co/collections/osunlp/quest 📌 Demo: https://huggingface.co/spaces/osunlp/QUEST

Amazing effort led by @jianxie_ (our 1st year student!!), Tianhe Lin, Zilu Wang. joint with @hhsun1 and the @osunlp team. thanks @amazon Xiangjun Wang for a gift that covers the compute and fruitful discussion.

2h33940

RETWEETS3

Yu Su@ysu_nlp

a demo of the system. try it out here! https://huggingface.co/spaces/osunlp/QUEST

4h2.4K83

Jian Xie@jianxie_

🚀Excited to announce QUEST today!

Benchmark numbers will fade, but the know-how behind them endures.

With QUEST: See how we synthesize diverse Deep Research tasks through a unified framework at scale. See how we train Deep Research agents through three stages: Mid-Training → SFT → RL. See how our caching system dramatically reduces API costs during training. See how our context management enables unbounded deep research.

We’ve released everything we can!

Yu Su@ysu_nlp

We trained a ~frontier Deep Research Agent on academic budget

> 32 H100s > 8K synthetic samples > fully open training infra + recipe (SFT, mid-training, RL) > models of diff sizes (2B -> 35B) ready to use out of the box

This is yet another demonstration of how the frontier of AI is changing. We have reached a point where open models + a small capable team + a few hundred Ks can produce specialized models with ~frontier capabilities. The future of AI doesn’t have to be held in a chokehold by a handful of closed models.

We've open-sourced everything we've built and learned from this project. Hope it helps the community build more!

📌 Project: https://osu-nlp-group.github.io/QUEST 📌 Paper: https://arxiv.org/abs/2605.24218 📌 Code: https://github.com/OSU-NLP-Group/QUEST 📌 Model Weights and Data: https://huggingface.co/collections/osunlp/quest 📌 Demo: https://huggingface.co/spaces/osunlp/QUEST

Amazing effort led by @jianxie_ (our 1st year student!!), Tianhe Lin, Zilu Wang. joint with @hhsun1 and the @osunlp team. thanks @amazon Xiangjun Wang for a gift that covers the compute and fruitful discussion.

4h1.6M24950

Zhehao Zhang@Zhehao_Zhang123

Excited to share our lab’s latest work on fully open deep research agents, led by @jianxie_! For anyone doing agentic post-training, it’s a gold mine: a full recipe (mid-training → SFT → RL), a rubric-tree data synthesis pipeline, and an open model family from 2B to 35B.

Yu Su@ysu_nlp

We trained a ~frontier Deep Research Agent on academic budget

> 32 H100s > 8K synthetic samples > fully open training infra + recipe (SFT, mid-training, RL) > models of diff sizes (2B -> 35B) ready to use out of the box

This is yet another demonstration of how the frontier of AI is changing. We have reached a point where open models + a small capable team + a few hundred Ks can produce specialized models with ~frontier capabilities. The future of AI doesn’t have to be held in a chokehold by a handful of closed models.

We've open-sourced everything we've built and learned from this project. Hope it helps the community build more!

📌 Project: https://osu-nlp-group.github.io/QUEST 📌 Paper: https://arxiv.org/abs/2605.24218 📌 Code: https://github.com/OSU-NLP-Group/QUEST 📌 Model Weights and Data: https://huggingface.co/collections/osunlp/quest 📌 Demo: https://huggingface.co/spaces/osunlp/QUEST

Amazing effort led by @jianxie_ (our 1st year student!!), Tianhe Lin, Zilu Wang. joint with @hhsun1 and the @osunlp team. thanks @amazon Xiangjun Wang for a gift that covers the compute and fruitful discussion.

4h940102

AlexT_Works@alext_works

@jianxie_ This framework is a massive leap forward for autonomous research agents.

4h93

茉妍💐@lcmoyan22

@jianxie_ 看到你的动态就来留个言，祝你安好🥰

3h59

Sidra Bank News@le123123bank

@jianxie_ Hello

4h53

Khoa Gà@KhoaNgu25383164

@jianxie_ Tuyệt quá

2h47

区块链小财迷@Daily_Solana_

@jianxie_ 一起关注起来

3h31

Kai Zhang@KaiZhang_CS

Check out one of the best open-source search agents trained by @jianxie_ !! glad to see early experience methods work on frontier agents!😀

Yu Su@ysu_nlp

We trained a ~frontier Deep Research Agent on academic budget

> 32 H100s > 8K synthetic samples > fully open training infra + recipe (SFT, mid-training, RL) > models of diff sizes (2B -> 35B) ready to use out of the box

This is yet another demonstration of how the frontier of AI is changing. We have reached a point where open models + a small capable team + a few hundred Ks can produce specialized models with ~frontier capabilities. The future of AI doesn’t have to be held in a chokehold by a handful of closed models.

We've open-sourced everything we've built and learned from this project. Hope it helps the community build more!

📌 Project: https://osu-nlp-group.github.io/QUEST 📌 Paper: https://arxiv.org/abs/2605.24218 📌 Code: https://github.com/OSU-NLP-Group/QUEST 📌 Model Weights and Data: https://huggingface.co/collections/osunlp/quest 📌 Demo: https://huggingface.co/spaces/osunlp/QUEST

Amazing effort led by @jianxie_ (our 1st year student!!), Tianhe Lin, Zilu Wang. joint with @hhsun1 and the @osunlp team. thanks @amazon Xiangjun Wang for a gift that covers the compute and fruitful discussion.