[BugFix] VLM RLVR add reward func

[PopSoda2002]

Description

Add a async_reward_fn similar with RLVR workflow:

# NOTE: load reward function dynamically if given as string
if isinstance(self.reward_fn, str):
    self.reward_fn = import_from_string(self.reward_fn)
    self.async_reward_fn = AsyncRewardWrapper(self.reward_fn)

Related Issue

Fixes #(issue)
#850

Type of Change

• Bug fix (non-breaking change that fixes an issue)

Checklist

• I have read the Contributing Guide
• I have run formatting tools (pre-commit or manual)
• I have run relevant unit tests and they pass
• I have added tests for new functionality
• I have updated documentation if needed
• My branch is up to date with main
• This PR introduces breaking changes (if yes, fill out details below)
• If this PR changes documentation, I have built and previewed it locally with
  jb build docs
• No critical issues raised by AI reviewers (/gemini review)

Breaking Change Details (if applicable):

Additional Context

---

Need help? Check the Contributing Guide or ask in
GitHub Discussions!

[gemini-code-assist]

Summary of Changes

Hello @PopSoda2002, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a bug by enhancing the VisionRLVRWorkflow to support dynamic loading of reward functions. This change allows reward functions to be specified as string paths, which are then imported and wrapped for asynchronous execution, thereby improving the configurability and robustness of the reward function handling within the VLM RLVR workflow. The update provides greater flexibility for defining and integrating reward mechanisms.

Highlights

• Dynamic Reward Function Loading: Implemented functionality to dynamically load the reward function if it is provided as a string path, enhancing flexibility and configuration options for the VisionRLVRWorkflow.
• Asynchronous Reward Wrapper: Introduced AsyncRewardWrapper to handle the dynamically loaded reward function, ensuring compatibility with asynchronous operations within the workflow.
• Type Hint Updates: Modified type hints for reward_fn and tokenizer parameters in the VisionRLVRWorkflow constructor to explicitly allow string types, reflecting the new dynamic loading capability.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds support for dynamically loading a reward function from a string path in VisionRLVRWorkflow, making it consistent with the parent RLVRWorkflow. The change is functionally correct and fixes a bug where using a string path for reward_fn would previously lead to an AttributeError. My review includes one suggestion to improve code style and maintainability by moving local imports to the top of the file, which also aligns the implementation more closely with existing patterns in the codebase.

[rchardx]

LGTM