Good First Issue List

# Good First Issue List

Trinity-RFT is a flexible and modular Reinforcement Fine-Tuning framework. We welcome contributions from the community to help improve and expand the framework.

As a starting point, here are some good first issues that new contributors can work on:

1. **Implement a New Workflow**
- **Description**: Create a new agentic workflow to tackle specific tasks.
- **Difficulty**: Easy or Medium
- **Labels**: `good first issue`, `workflow`
- **Resources**: Check out the [Workflow Development Guide](https://modelscope.github.io/Trinity-RFT/en/main/tutorial/develop_workflow.html) for step-by-step instructions.
- **Examples**:
- Gomoku, Sudoku, or other interesting game playing workflows
- Workflows to solve benchmarks like [Multi-hop QA](https://arxiv.org/abs/2204.09140), [MuSiQue](https://arxiv.org/abs/2108.00573), etc.
- Workflows to adapt to popular agent frameworks like [LangChain](https://www.langchain.com/), [AutoGen](https://github.com/microsoft/autogen), etc.
- ...

2. **Implement a New RL Algorithm**
- **Description**: Implement a new reinforcement learning algorithm to improve training efficiency or performance.
- **Difficulty**: Medium
- **Labels**: `good first issue`, `algorithm`
- **Resources**: Refer to the [Algorithm Development Guide](https://modelscope.github.io/Trinity-RFT/en/main/tutorial/develop_algorithm.html) for implementation tutorials.
- **Examples**:
- Implement newly proposed RL algorithms, e.g., [M2PO](https://arxiv.org/pdf/2510.01161), [BAPO](https://arxiv.org/pdf/2510.18927).
- Optimize existing algorithms by improving their efficiency or stability.
- ...

3. **Implement a New Experience Operator**
- **Description**: Develop a new operator for experience data filtering, augmentation, or reward shaping.
- **Difficulty**: Easy or Medium
- **Labels**: `good first issue`, `operator`
- **Resources**: See the [Operator Development Guide](https://modelscope.github.io/Trinity-RFT/en/main/tutorial/develop_operator.html) for guidance.
- **Examples**:
- Implement an operator to filter out low-quality experiences based on predefined criteria.
- Implement an operator to refine rewards by comparing experiences generated from different runs of the same task.
- ...

4. **Improve Examples and Documentation**
- **Description**: Enhance the existing examples and documentation to help new users get started with Trinity-RFT.
- **Difficulty**: Easy
- **Labels**: `good first issue`, `documentation`
- **Resources**: Check the existing [Examples](https://github.com/modelscope/Trinity-RFT/tree/main/examples) and [Documentation](https://modelscope.github.io/Trinity-RFT/en/main/index.html) for areas of improvement.
- **Examples**:
- Add examples for workflows or algorithms implemented but not yet documented in the examples directory.
- Improve existing documentation for clarity and completeness.
- ...

Besides these tasks for beginners, we also have more challenging issues for experienced contributors, such as:

- Reduce the bubble caused by decoupled Explorer / Trainer to improve resource utilization.
- Improve the efficiency of the experience buffer.
- Add partial rollout support to the Explorer to avoid resource waste caused by the long-tail effect of rollouts in agentic RL scenarios.
- Add popular inference backends like [SGLang](https://github.com/sgl-project/sglang).
- ...

If you're interested in working on any of these issues, please feel free to comment on the issue or open a pull request. We look forward to your contributions!