optimize_anything: A Universal API for Optimizing any Text Parameter

• URL: http://arxiv.org/abs/2605.19633v1
• Date: Tue, 19 May 2026 10:18:12 GMT
• Title: optimize_anything: A Universal API for Optimizing any Text Parameter
• Abstract summary: We show a single AI-based optimization system-supporting single-task search, multi-task search with cross-problem transfer, and generalization to unseen inputs.<n>We show for the first time that text optimization with LLM-based search is a general-purpose problem-solving paradigm.
• Score: 98.42497715725356
• License: http://creativecommons.org/licenses/by/4.0/
• 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 .

Related papers

• InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents [15.892896819368751]
  We introduce InferenceBench, where an agent must deploy an OpenAI-compatible inference server and optimize the speed of LLM inference.<n>Three optimization scenarios isolate distinct bottlenecks of inference.<n>Agents reliably improve over a naive PyTorch baseline.<n>Overall, InferenceBench reflects the ability of agents to operate in an open-ended AI engineering setting.
  arXiv  Detail & Related papers  (2026-05-20T15:55:21Z)
• cuGenOpt: A GPU-Accelerated General-Purpose Metaheuristic Framework for Combinatorial Optimization [12.89168708039677]
  cuGenOpt is a general-purpose metaheuristic framework that addresses all three dimensions simultaneously.<n>At the engine level, cuGenOpt adopts a unified encoding abstraction (permutation, binary, integer), a two-level operator selection mechanism, and hardware-aware resource management.<n>Experiments show cuGenOpt suites outperforms general MIP solvers by orders of magnitude, competitive quality against specialized solvers, and attains 4.73% gap on TSP-442 within 30s.
  arXiv  Detail & Related papers  (2026-03-19T17:19:21Z)
• A Preprocessing Framework for Efficient Approximate Bi-Objective Shortest-Path Computation in the Presence of Correlated Objectives [17.59787357130767]
  We consider the bi-objective shortest-path (BOSP) problem in the presence of correlated objectives.<n>BOSP is generally computationally challenging as the size of the search space is exponential in the number of objective functions and the graph size.<n>We propose an efficient algorithm that reduces the search effort in the presence of correlated objectives.
  arXiv  Detail & Related papers  (2025-05-28T11:26:14Z)
• A*-Decoding: Token-Efficient Inference Scaling [0.0]
  Inference-time scaling has emerged as a powerful alternative to parameter scaling for improving language model performance.<n>We introduce A*-decoding, a search-based inference-time strategy that builds on the A* search algorithm to optimally utilize a fixed compute budget.<n>Our work demonstrates how thoughtful inference-time strategies can enhance reasoning in SLMs, pointing toward future advances in more efficient and scalable language model deployment.
  arXiv  Detail & Related papers  (2025-05-19T19:19:48Z)
• Scaling LLM Inference with Optimized Sample Compute Allocation [56.524278187351925]
  We propose OSCA, an algorithm to find an optimal mix of different inference configurations. Our experiments show that with our learned mixed allocation, we can achieve accuracy better than the best single configuration. OSCA is also shown to be effective in agentic beyond single-turn tasks, achieving a better accuracy on SWE-Bench with 3x less compute than the default configuration.
  arXiv  Detail & Related papers  (2024-10-29T19:17:55Z)
• Towards General and Efficient Online Tuning for Spark [55.30868031221838]
  We present a general and efficient Spark tuning framework that can deal with the three issues simultaneously. We have implemented this framework as an independent cloud service, and applied it to the data platform in Tencent.
  arXiv  Detail & Related papers  (2023-09-05T02:16:45Z)
• Massively Parallel Genetic Optimization through Asynchronous Propagation of Populations [50.591267188664666]
  Propulate is an evolutionary optimization algorithm and software package for global optimization. We provide an MPI-based implementation of our algorithm, which features variants of selection, mutation, crossover, and migration. We find that Propulate is up to three orders of magnitude faster without sacrificing solution accuracy.
  arXiv  Detail & Related papers  (2023-01-20T18:17:34Z)
• Efficient Non-Parametric Optimizer Search for Diverse Tasks [93.64739408827604]
  We present the first efficient scalable and general framework that can directly search on the tasks of interest. Inspired by the innate tree structure of the underlying math expressions, we re-arrange the spaces into a super-tree. We adopt an adaptation of the Monte Carlo method to tree search, equipped with rejection sampling and equivalent- form detection.
  arXiv  Detail & Related papers  (2022-09-27T17:51:31Z)
• A Simple Evolutionary Algorithm for Multi-modal Multi-objective Optimization [0.0]
  We introduce a steady-state evolutionary algorithm for solving multi-modal, multi-objective optimization problems (MMOPs) We report its performance on 21 MMOPs from various test suites that are widely used for benchmarking using a low computational budget of 1000 function evaluations.
  arXiv  Detail & Related papers  (2022-01-18T03:31:11Z)
• Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information [78.78486761923855]
  In many real world problems, we want to infer some property of an expensive black-box function f, given a budget of T function evaluations. We present a procedure, InfoBAX, that sequentially chooses queries that maximize mutual information with respect to the algorithm's output. On these problems, InfoBAX uses up to 500 times fewer queries to f than required by the original algorithm.
  arXiv  Detail & Related papers  (2021-04-19T17:22:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.