Skip to content

Update README.md #240

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 28, 2025
Merged

Update README.md #240

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions examples/algotune/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,8 @@
This report documents a comprehensive optimization journey using OpenEvolve on the AlgoTune benchmark suite. Through systematic experimentation with model configurations, prompt engineering, and evolutionary parameters, we achieved significant performance improvements across 8 algorithmic tasks.

**Final Results:**
- **Best AlgoTune Score: 1.984x** (harmonic mean across 7 successful tasks)
- **Best AlgoTune Score: 1.984x** (harmonic mean across 8 successful tasks)
- **Major Breakthroughs:** JAX optimization discovery (321x speedup), FFT convolution (256x), parameter optimization (3.2x)
- **Success Rate:** 7/8 tasks completed successfully
- **Total Evolution Time:** ~200 minutes for full benchmark

## The Optimization Journey
Expand Down Expand Up @@ -262,4 +261,4 @@ This comprehensive optimization journey demonstrates OpenEvolve's remarkable cap

---

*This report represents the culmination of extensive experimentation with OpenEvolve's evolutionary code optimization capabilities on the AlgoTune benchmark suite, providing a roadmap for future AI-assisted algorithmic discovery.*
*This report represents the culmination of extensive experimentation with OpenEvolve's evolutionary code optimization capabilities on the AlgoTune benchmark suite, providing a roadmap for future AI-assisted algorithmic discovery.*