Add example for data augmentation in tuner

[lingzhq]

📝 PR Type

• Add new sample
• Update existing sample
• Add new test cases
• Fix test failures
• Documentation/Configuration update

---

📚 Description

Add an example for data augmentation strategy of Agentscope-Tuner.

---

🧪 Testing Validation

Follow the README to run the examples.

---

✅ Checklist

Please complete the following checks before submitting the PR:

• All sample code has been formatted with pre-commit run --all-files
• All new/modified test cases have passed (run pytest tests/)
• Test coverage has not decreased (if applicable)
• Sample code follows agentscope best practices (e.g., config management, logging)
• Related documentation in agentscope-samples has been updated (e.g., README.md)

[cla-assistant]

All committers have signed the CLA.

[Copilot]

Pull request overview

This PR adds a new example demonstrating data augmentation strategies for AgentScope-Tuner, specifically focusing on difficulty-based task selection for training a math problem-solving ReAct agent.

Changes:

• Adds a complete data augmentation example with configuration for both random and difficulty-based task selectors
• Includes data preparation script to transform the LLM360/guru-RL-92k dataset into GSM8K format
• Provides comprehensive documentation explaining data-centric training approaches

Reviewed changes

Copilot reviewed 5 out of 6 changed files in this pull request and generated 5 comments.

Show a summary per file

File	Description
tuner/data_augment/prepare_data.py	Script to download and transform math dataset from HuggingFace, extracting difficulty features
tuner/data_augment/main.py	Main training script implementing ReAct agent workflow and GSM8K judge function with tuner integration
tuner/data_augment/config_random.yaml	Configuration file for baseline experiment using random task selector
tuner/data_augment/config_difficulty.yaml	Configuration file for advanced experiment using difficulty-based task selector
tuner/data_augment/README.md	Comprehensive documentation explaining the data-centric approach, setup, and usage

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[lingzhq]

Fixed comments from co-pilot.