optimize_anything: Unified Text Optimization can Outperform Specialized Systems
Description
Can a single LLM-based optimization system match specialized tools across fundamentally different domains? We show that when optimization problems are formulated as improving a text artifact evaluated by a scoring function, a single AI-based optimization system--supporting single-task search, multi-task search with cross-problem transfer, and generalization to unseen inputs--achieves state-of-the-art results across six diverse tasks. Our system discovers agent architectures that nearly triple Gemini Flash's ARC-AGI accuracy (32.5\% → 89.5\%), finds scheduling algorithms that cut cloud costs by 40\%, generates CUDA kernels where 87\% match or beat PyTorch, and outperforms AlphaEvolve's reported circle packing solution (n=26). Ablations reveal that structured diagnostic feedback (side information) yields faster convergence and higher final scores than score-only feedback, and that multi-task search can outperform independent optimization given equivalent per-problem budget through cross-task transfer. Together, we show for the first time that text optimization with LLM-based search is a general-purpose problem-solving paradigm, unifying tasks traditionally requiring domain-specific algorithms under a single framework.
Notes
Files
lukeleeai/optany_artifact-v1.0.zip
Files
(67.5 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:6c940050ce7a717b847d17f4ee88b81f
|
67.5 MB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/lukeleeai/optimize_anything_artifact/tree/v1.0 (URL)
Software
- Repository URL
- https://github.com/lukeleeai/optimize_anything_artifact