PyTorch Conf deck: train your own agents in 2026 with SFT, GRPO and TRL + OpenEnv
SergioPaniego · x · 2026-10-22
Sergio Paniego shared the full slide deck from his talk at PyTorch Conf North America on how agents get trained in 2026 — and how to do it yourself.
The deck walks through the complete agent training pipeline: SFT → distillation → GRPO → RL environments → training through the harness, all built with TRL + OpenEnv. The slides are packed with links, making them a practical roadmap for developers who want to get hands-on with agent RL training.
Related event: PyTorch Conf Slides Outline 2026 Agent Training Pipeline(2 posts)→
More from coding & agent
- Quant-Arena: 9 LLM agents trade real A-shares, only 4 profit and none beat equal-weight — mhdfaran · 2026-10-22
- Pi Coding Agent Gets a Full Rust Port via Claude, Under 90MB Memory — jasonkneen · 2026-10-22
- Securing coding agents with Docker Sandboxes and edge LLM inference at ATO — HowDevelop · 2026-10-22
- Free book 'LangGraph in Small Pieces' teaches agents from blocks to production — truckkicker · 2026-10-22
- What Everyone Is Getting Wrong About Context, per a Founder's New Article — shensi · 2026-10-22
- Cloudflare's AI security-audit skill tops GitHub with 38.5k stars — alex_verem · 2026-10-22