optimize_anything: A Universal API for Optimizing any Text Parameter
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910236138274816 |
|---|---|
| author | Agrawal, Lakshya A Lee, Donghyun Tan, Shangyin Ma, Wenjie Elmaaroufi, Karim Sandadi, Rohit Seshia, Sanjit A. Sen, Koushik Klein, Dan Stoica, Ion Gonzalez, Joseph E. Khattab, Omar Dimakis, Alexandros G. Zaharia, Matei |
| author_facet | Agrawal, Lakshya A Lee, Donghyun Tan, Shangyin Ma, Wenjie Elmaaroufi, Karim Sandadi, Rohit Seshia, Sanjit A. Sen, Koushik Klein, Dan Stoica, Ion Gonzalez, Joseph E. Khattab, Omar Dimakis, Alexandros G. Zaharia, Matei |
| contents | 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% to 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 across three domains reveal that actionable side information yields faster convergence and substantially higher final scores than score-only feedback, and that multi-task search outperforms independent optimization given equivalent per-problem budget through cross-task transfer, with benefits scaling with the number of related tasks. 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. We open-source optimize\_anything with support for multiple backends as part of the GEPA project at https://github.com/gepa-ai/gepa . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19633 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | optimize_anything: A Universal API for Optimizing any Text Parameter Agrawal, Lakshya A Lee, Donghyun Tan, Shangyin Ma, Wenjie Elmaaroufi, Karim Sandadi, Rohit Seshia, Sanjit A. Sen, Koushik Klein, Dan Stoica, Ion Gonzalez, Joseph E. Khattab, Omar Dimakis, Alexandros G. Zaharia, Matei Computation and Language Artificial Intelligence Machine Learning Neural and Evolutionary Computing Software Engineering 68T05, 68T07, 68T20, 68T50, 68W50, 90C26, 90C59, 52C15 I.2.6; I.2.7; I.2.8; I.2.11; D.1.2; D.2.2; G.1.6; F.2.2 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% to 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 across three domains reveal that actionable side information yields faster convergence and substantially higher final scores than score-only feedback, and that multi-task search outperforms independent optimization given equivalent per-problem budget through cross-task transfer, with benefits scaling with the number of related tasks. 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. We open-source optimize\_anything with support for multiple backends as part of the GEPA project at https://github.com/gepa-ai/gepa . |
| title | optimize_anything: A Universal API for Optimizing any Text Parameter |
| topic | Computation and Language Artificial Intelligence Machine Learning Neural and Evolutionary Computing Software Engineering 68T05, 68T07, 68T20, 68T50, 68W50, 90C26, 90C59, 52C15 I.2.6; I.2.7; I.2.8; I.2.11; D.1.2; D.2.2; G.1.6; F.2.2 |
| url | https://arxiv.org/abs/2605.19633 |