optany: Unified Text Optimization can Outperform Specialized Systems
Lakshya A Agrawal (University of California, Berkeley), Donghyun Lee (University of California, Berkeley), Wenjie Ma (University of California, Berkeley), Karim Elmaaroufi (University of California, Berkeley), Rohit Sandadi (University of California, Berkeley), Shangyin Tan (University of California, Berkeley), Sanjit A. Seshia (University of California, Berkeley), Koushik Sen (University of California, Berkeley), Dan Klein (University of California, Berkeley), Ion Stoica (University of California, Berkeley), Joseph Gonzalez (University of California, Berkeley), Omar Khattab (Massachusetts Institute of Technology), Alexandros G. Dimakis (University of California, Berkeley), Matei Zaharia (University of California, Berkeley)
Architectural Patterns & Composition
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\% → 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.
