Tutorial: Train a multi-turn tool-using agent with Tunix
Google Developers Blog published a tutorial for training a multi-turn, tool-using LLM agent with Tunix, Gemma 4 E2B, and Cloud TPU v6e-8. The example uses the Plane Strike game and reports that 100 steps of agentic GRPO raised held-out win rate from 9.4% to about 95% while reducing average game length to roughly 16 strikes. The complete training code is available in a GitHub repository.
The tutorial provides a concrete implementation and code for multi-turn agentic reinforcement learning with tools on Google TPUs, offering developers a reproducible starting point.
Multi-Turn Agentic Reinforcement Learning with Tunix and Gemma 4 on Google TPUs - Google Developers Blog
Multi-Turn Agentic Reinforcement Learning with Tunix and Gemma 4 on Google TPUs
NOV. 19, 2026
Wei Wei Developer Advocate
