# Roadmap

Source: https://club.penguin.ooo/roadmap/

Welcome to the Shared RSI Community! We focus on open-source research and engineering for Recursive Self-Improvement (RSI). Previously, we built [GDPevo](https://arxiv.org/pdf/2608.03764), an enterprise-grade evaluation benchmark for self-evolving agents, and authored a comprehensive [survey on RSI research](https://arxiv.org/abs/2610.14625).

Currently, we are iterating along the following tracks:
- **Data**: Curating agent Benchmark datasets and Evaluation results to build **the largest RSI Leaderboard**.
- **Survey**: Surveying **the latest RSI papers** and reorganizing their taxonomy to further improve the [Awesome RSI](https://github.com/Prism-Shadow/awesome-rsi) repository.
- **Framework**: Optimizing the [PenguinHarness](https://penguin.ooo/) unified RSI framework to build **the most comprehensive self-evolving harness**.

## Evolution Roadmap

> If you are new to core concepts such as Agents, Self-Evolution (RSI), Harnesses, the distinction between Harness-Level and Model-Level Evolution, and Benchmarks, check out **[Basic Concepts](https://club.penguin.ooo/roadmap/concepts/)** first.

In **Stage 1**, we focus on **Data**, **Survey**, and **Harness-Level Evolution**. Because harness-level evolution does not require updating underlying model weights, it demands significantly less GPU compute and lower experimental cost, while producing human-interpretable prompts, skills, and tools that transfer across models—making RSI far more accessible and inclusive for the broader research and developer community.

In **Stage 2**, building upon the benchmarks, algorithm plugins, and high-quality evolution traces accumulated by the community, we will expand into **Model-Level Evolution**:
- **Trajectory Synthesis & Distillation**: Leveraging high-scoring execution traces and evolved skill assets produced by self-evolving harnesses across diverse benchmarks in Stage 1 to synthesize and curate training data, internalizing explicit external experience into model weights.
- **Self-Evolving SFT & Agentic RL**: Driven by verifiable reward signals from standardized community sandboxes and automated evaluators, conducting supervised fine-tuning (SFT) and agentic reinforcement learning (Agentic RL) on long-horizon tasks to directly strengthen the base model's planning, tool use, and self-correction capabilities.
- **Harness × Model Co-Evolution**: Closing the bi-level loop between outer-loop harness search and inner-loop parameter updates—where stronger harnesses synthesize higher-ceiling trajectories for model training, and stronger models in turn empower harnesses to tackle more complex task boundaries.

1. Stage 1: Data (RSI Leaderboard), Survey (Awesome RSI), Harness Evolution (PenguinHarness).
2. Stage 2 (Model-Level Evolution): Trajectory Synthesis (Experience Distillation), Model Training (SFT & Agentic RL), Co-Evolution (Harness × Model).

## How to Participate

For detailed workflows, please refer to the **[Workflow](https://club.penguin.ooo/workflow/)** pages:
- How to submit a Benchmark: [../workflow/benchmark.md](https://club.penguin.ooo/workflow/benchmark/)
- How to submit an Evaluation: [../workflow/evaluation.md](https://club.penguin.ooo/workflow/evaluation/)
- How to submit an Algorithm Plugin: [../workflow/algorithm.md](https://club.penguin.ooo/workflow/algorithm/)
- How to contribute to PenguinHarness: [../workflow/harness.md](https://club.penguin.ooo/workflow/harness/)
- How to submit papers to Awesome RSI: [../workflow/survey.md](https://club.penguin.ooo/workflow/survey/)

We hold **[Bi-weekly Sync](https://club.penguin.ooo/rfcs/rfc-0004-meeting/)** community meetings for discussion, with meeting links posted in our community group the day before.

We warmly welcome everyone to join our open-source community, and we commit to the following for contributors:
- Active monthly contributors will receive **token resource packages** for frontier models such as Gemini.
- Open-source contributors with significant contributions will be credited as authors in our **open-source repositories**.
- Contributors who submit original methods or original experimental results will be invited as co-authors on our upcoming **papers**.