[recipe] feat: Add InfiGUI-G1 recipe for MLLM GUI grounding

[Sirius-L1]

What does this PR do?

This PR introduces a new recipe, infigui-g1, for training Multimodal Large Language Models (MLLMs) in GUI grounding tasks. This recipe implements a reinforcement learning approach that significantly improves the model's ability to understand and interact with graphical user interfaces.

Checklist Before Starting

• Search for similar PRs. Paste at least one query link here: https://github.com/search?q=repo%3Avolcengine%2Fverl+gui&type=pullrequests
• Format the PR title as [{modules}] {type}: {description} (This will be checked by the CI)
  • {modules} include fsdp, megatron, sglang, vllm, rollout, trainer, ci, training_utils, recipe, hardware, deployment, ray, worker, single_controller, misc, perf, model, algo, env, tool, ckpt, doc, data
  • If this PR involves multiple modules, separate them with , like [megatron, fsdp, doc]
  • {type} is in feat, fix, refactor, chore, test
  • If this PR breaks any API (CLI arguments, config, function signature, etc.), add [BREAKING] to the beginning of the title.
  • Example: [BREAKING][fsdp, megatron] feat: dynamic batching

Test

The effectiveness of this recipe has been validated through experiments. Key results are as follows:

• The training curves for reward, validation accuracy, and exploration success rate all show a upward trend.
• After 156 steps of training on sample data, the 3b model achieves a score of 41.2 on the screenspot-pro benchmark, a substantial improvement over the base model's score of 18.2.

API and Usage Example

The recipe is self-contained and can be run using the provided scripts. For example, to run training with the 3B parameter model:

# In verl path
bash recipe/infigui-g1/run_3b.sh

Design & Code Changes

This PR adds a new, independent recipe located in recipe/infigui-g1/. The changes are fully encapsulated within this directory and do not affect any other part of the codebase.

The new files include:

• recipe/infigui-g1/README.md: An introduction to the recipe.
• recipe/infigui-g1/run_3b.sh, run_7b.sh: Scripts to launch training.
• recipe/infigui-g1/reward_fn.py: Custom reward function implementation.

Checklist Before Submitting

Important

Please check all the following items before requesting a review, otherwise the reviewer might deprioritize this PR for review.

• Read the Contribute Guide.
• Apply pre-commit checks: pre-commit install && pre-commit run --all-files --show-diff-on-failure --color=always
• Add / Update the documentation.
• Add unit or end-to-end test(s) to the CI workflow to cover all the code. If not feasible, explain why: ...
• Once your PR is ready for CI, send a message in the ci-request channel in the verl Slack workspace. (If not accessible, please try the Feishu group (飞书群).)

[CLAassistant]

All committers have signed the CLA.

[gemini-code-assist]

Code Review

This pull request introduces a new recipe for GUI grounding. The implementation of the custom reward function in reward_fn.py is mostly solid, but I've identified two high-severity issues that could affect the correctness of the reward calculation. One issue is related to the robustness of JSON parsing from the model's output, and the other concerns the use of direct equality comparison for floating-point numbers when checking for collinear points. I've provided suggestions to fix both. The rest of the changes, including the run scripts and documentation, look good.