---
format: "aidr-story-markdown/v1"
id: "208e913775b0ef64bf51e0c465d01c8e796324a20d2815ebd588ab44210714df"
canonical_url: "https://aidr.today/208e9137?lang=en"
title: "Multi-Turn Agentic Reinforcement Learning with Tunix and Gemma 4 on Google TPUs"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-19T17:17:50.000Z"
category: "Frameworks"
topics: ["google","agent","framework"]
source_urls: ["https://developers.googleblog.com/multi-turn-agentic-reinforcement-learning-with-tunix-and-gemma-4-on-google-tpus/"]
summary: "This post walks developers through training a multi-turn, tool-using LLM agent using Tunix and Gemma 4 on Cloud TPUs. By leveraging agentic Group Relative Policy Optimization (GRPO) and asynchronous vLLM rollouts, the approach significantly improves complex reasoning and tool compliance in interactive environments."
---

# Multi\-Turn Agentic Reinforcement Learning with Tunix and Gemma 4 on Google TPUs

> [Open the canonical story](<https://aidr.today/208e9137?lang=en>)

**Published:** 2026-11-19T17:17:50.000Z
**Category:** Frameworks
**Topics:** google, agent, framework

## Summary

This post walks developers through training a multi\-turn, tool\-using LLM agent using Tunix and Gemma 4 on Cloud TPUs\. By leveraging agentic Group Relative Policy Optimization \(GRPO\) and asynchronous vLLM rollouts, the approach significantly improves complex reasoning and tool compliance in interactive environments\.

## Sources

- [Story source](<https://developers.googleblog.com/multi-turn-agentic-reinforcement-learning-with-tunix-and-gemma-4-on-google-tpus/>)

