Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
sergiopaniego 
posted an update 17 days ago
Post
3,078
how do you post-train an agent?

we laid it out as a 5-step curriculum, from SFT to RL through a real harness, with livestreams, code and docs for each step

https://huggingface.co/blog/huggingface/train-agents
MuhammadAwais7

awesome
Twu31

The move from single-turn rewards to full runs in a real agent harness seems especially useful for diagnosing tool-use failures. For someone working through the curriculum, is there a small held-out task set you'd suggest keeping fixed across SFT, distillation and RL? That would make it easier to tell gains from training from changes in the harness or task mix.
In this post