Pinned Loading

1. wq-will/SimpleTES wq-will/SimpleTES Public

   A general framework for strategically scaling evaluation-driven discovery loops, discovering state-of-the-art solutions on 21 open-ended problems.

   C++ 103 12

2. harbor-framework/harbor harbor-framework/harbor Public

   Harbor is a framework for running agent evaluations and creating and using RL environments.

   Python 2k 1k

3. Yuanpei-Intelligence/YPPF Yuanpei-Intelligence/YPPF Public

   Yuanpei Profile

   Python 38 65

4. YWolfeee/Training-Free-Guidance YWolfeee/Training-Free-Guidance Public

   Code for TFG: Unified Training-Free Guidance for Diffusion Models

   Python 84 10

5. harbor-framework/terminal-bench harbor-framework/terminal-bench Public

   A benchmark for LLMs on complicated tasks in the terminal

   Python 2.2k 514

6. SLD SLD Public

   [ICLR26] AI-based scaling law discovery

   Python 28