Remote Agent Quickstart ↗

fireworks tutorial beginner agents fine-tuning
no
Summary: Train an SVG drawing agent running in a remote environment

Original Documentation

Documentation Index#

Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt Use this file to discover all available pages before exploring further.

Train an SVG drawing agent running in a remote environment

Reinforcement Fine-Tuning (RFT) is free for models under 16B parameters. When creating an RFT job in the UI, filter for free tuning models in the model selection area on the fine-tuning creation page. If kicking off jobs from the terminal, you can find the model ID from the Model Library. Note: SFT and DPO jobs are billed per training token for all model sizes—see the pricing page for details.

Following the RFT Overview? This is the Remote Agent Training path—for training agents that run in your production infrastructure.

In this quickstart, you’ll train an agent to generate SVG drawings. Your agent runs in a remote server (Vercel), which means rollouts happen remotely while Fireworks handles the training. This approach lets you train agents that already live in your production environment.

Here’s a quick walkthrough: