Hugging Face's AI agent that automates post-training
An open-source AI agent that fully automates post-training: reads arXiv papers, fixes & creates datasets, runs training jobs, debugs failures, and iterates all by itself. Results: +22 pts on GPQA in 10h and +60% on HealthBench. The future of ML research is here.
Introducing ml-intern, the agent that just automated the post-training team
at Hugging Face
It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU sandboxes, iterates and builds deeply research-backed models for any use case. All built on the Hugging Face ecosystem.
It can pull off crazy things:
- it trained the best model for scientific reasoning. It went through citations from the official benchmark paper. Found OpenScience and NemoTron-CrossThink, added 7 difficulty-filtered dataset variants from ARC/SciQ/MMLU, and ran 12 SFT runs on Qwen3-1.7B. This pushed the score 10% → 32% on GPQA in under 10h. Claude Code's best: 22.99%.
- In healthcare settings it inspected available datasets, concluded they were too low quality, and wrote a script to generate 1100 synthetic data points from scratch for emergencies, hedging, multilingual etc. Then upsampled 50x for training. Beat Codex on HealthBench by 60%.
- For competitive mathematics, it wrote a full GRPO script, launched training with A100 GPUs on http://hf.co/spaces, watched rewards claim and then collapse, and ran ablations until it succeeded. All fully backed by papers, autonomously.
How it works?
ml-intern makes full use of the HF ecosystem:
- finds papers on arxiv and http://hf.co/papers, reads them fully, walks citation graphs, pulls datasets referenced in methodology sections and on http://hf.co/datasets
- browses the Hub, reads recent docs, inspects datasets and reformats them before training so it doesn't waste GPU hours on bad data
- launches training jobs on HF Jobs if no local GPUs are available, monitors runs, reads its own eval outputs, diagnoses failures, retrains
ml-intern deeply embodies how researchers work and think. It knows how data should look like and what good models feel like.
Releasing it today as a CLI and a web app you can use from your phone/desktop.
CLI: https://github.com/huggingface/m...
Web + mobile: https://huggingface.co/spaces/sm...
And the best part? Hugging Face also provisioned 1k$ GPU resources and Anthropic credits for the quickest to use it
About ml-intern on Product Hunt
“Hugging Face's AI agent that automates post-training”
ml-intern launched on Product Hunt on April 22nd, 2026 and earned 79 upvotes and 2 comments, placing #22 on the daily leaderboard. An open-source AI agent that fully automates post-training: reads arXiv papers, fixes & creates datasets, runs training jobs, debugs failures, and iterates all by itself. Results: +22 pts on GPQA in 10h and +60% on HealthBench. The future of ML research is here.
On the analytics side, ml-intern competes within Artificial Intelligence, GitHub and Science — topics that collectively have 509.8k followers on Product Hunt. The dashboard above tracks how ml-intern performed against the three products that launched closest to it on the same day.
Who hunted ml-intern?
ml-intern was hunted by Aymeric Roucher. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of ml-intern including community comment highlights and product details, visit the product overview.
Aymeric Roucher