Hi @taesiri 🤗
Niels here from the open-source team at Hugging Face. I discovered your excellent work on GEM through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2510.01051.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo for instance), you can also claim the paper as yours which will show up on your public profile at HF, add Github and project page URLs.
It's fantastic to see that the GEM baselines (e.g., Qwen3-1.7B-Base-GEM-GuessTheNumber-v0) and the MCPMark environment are already hosted on the axon-rl 🤗 Hub organization, greatly improving their discoverability/visibility!
I also noticed that your paper introduces a "diverse suite of environments" within GEM (e.g., GuessTheNumber-v0, Mastermind-v0, GSM8K, CodeContest, Circuit Logic). These serve as new interactive tasks and benchmarks for LLM agents. It would be awesome to make these environments themselves available on the 🤗 Hub as datasets! This would allow users to easily:
from datasets import load_dataset
dataset = load_dataset("axon-rl/gem-guessthenumber-v0")and similar for other environments you provide.
See here for a guide on uploading datasets: https://huggingface.co/docs/datasets/loading. We can add tags so that people find them when filtering https://huggingface.co/datasets. Additionally, the dataset viewer allows people to quickly explore the data in the browser.
After uploaded, we can also link these datasets to the paper page (read here) so people can discover your work.
Let me know if you're interested or need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @taesiri 🤗
Niels here from the open-source team at Hugging Face. I discovered your excellent work on GEM through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2510.01051.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo for instance), you can also claim the paper as yours which will show up on your public profile at HF, add Github and project page URLs.
It's fantastic to see that the GEM baselines (e.g.,
Qwen3-1.7B-Base-GEM-GuessTheNumber-v0) and theMCPMarkenvironment are already hosted on theaxon-rl🤗 Hub organization, greatly improving their discoverability/visibility!I also noticed that your paper introduces a "diverse suite of environments" within GEM (e.g.,
GuessTheNumber-v0,Mastermind-v0,GSM8K,CodeContest,Circuit Logic). These serve as new interactive tasks and benchmarks for LLM agents. It would be awesome to make these environments themselves available on the 🤗 Hub as datasets! This would allow users to easily:and similar for other environments you provide.
See here for a guide on uploading datasets: https://huggingface.co/docs/datasets/loading. We can add tags so that people find them when filtering https://huggingface.co/datasets. Additionally, the dataset viewer allows people to quickly explore the data in the browser.
After uploaded, we can also link these datasets to the paper page (read here) so people can discover your work.
Let me know if you're interested or need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗