Hugging Face workshop: enterprise RL, environment design and scaling agent training with open models
Hugging Face · youtube · 2026-10-26
Hugging Face released the in-person "Training Agents IRL" workshop on post-training agents with open models. Four talks (Microsoft on enterprise RL, Mercor on environments and benchmarks, RadixArk on scaling agent RL with Miles, BenchFlow on OpenEnv Arena) plus a panel and Q&A. All slides are downloadable, backed by a four-class livestream series covering trace fine-tuning, distillation, GRPO RL, and reward-to-environment design, with full code, TRL trainer docs, and curriculum.
More from coding & agent
- Rethinking dependencies in the agent era: drop libs that save 20 lines of code — gethackteam · 2026-10-26
- RustGIS hits 2,000 GitHub stars in two weeks with agent-first architecture — giswqs · 2026-10-26
- Vercel Ships 12 New Products at Its 2026 Conference as It Races Rivals for the Agent Entry Point — FinanceYF5 · 2026-10-26
- Build an AI agent from scratch in under 50 lines of pure Python: ReAct loop tutorial — adnan_hashmi · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- Security tip: use AI agents to build a NIST CSF knowledge base for incident response — prasanna_says · 2026-10-26