optimize_anything: A Universal API for Optimizing any Text Parameter

TL;DR

This paper introduces optimize extunderscore anything, a universal LLM-based optimization system that effectively solves diverse text-based problems across multiple domains, achieving state-of-the-art results and unifying various task-specific algorithms.

Contribution

The authors present a single, general-purpose AI optimization framework capable of handling multiple domains and tasks, outperforming specialized tools and enabling cross-task transfer and generalization.

Findings

Nearly tripled Gemini Flash's ARC-AGI accuracy (32.5% to 89.5%)

Reduced cloud costs by 40% through optimized scheduling algorithms

Generated CUDA kernels with 87% matching or outperforming PyTorch implementations

Abstract

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 .