Agents
Agentic RL is hard at every layer: environments, training infra, and algorithms. So we’re open-sourcing all of it. For environments, that me…
Agentic RL is hard at every layer: environments, training infra, and algorithms. So we’re open-sourcing all of it. For environments, that means both the dataset and the scalable synthesis + quality-co
Agentic RL is hard at every layer: environments, training infra, and algorithms. So we’re open-sourcing all of it. For environments, that means both the dataset and the scalable synthesis + quality-control pipeline behind it. 🤗 https://huggingface.co/datasets/camel-ai/SETA-Env 🐙 https://github.com/camel-ai/seta/tree/main/datasynth
Related
- AgentTrove: new agentic dataset with 1.7M samples Thanks to OpenThoughts for this great work The @huggingface Hub needs more agentic dataset…
- Most people training agentic LLMs with RL right now have a silently broken training loop and have no idea. Here's the trap: single-turn RL w…
- Dataset Curation 3, this time agentic tool calling traces! https://huggingface.co/datasets/DJLougen/Acta
- We’re the only major open-source agentic sandbox platform and the only widely used sandbox platform licensed under Apache 2.0. Like LLMs, sa…
Source: Clem Delangue (X) | 2026-10-02