优化器即智能体：跨提示、程序与机器学习工作流的推理驱动搜索

摘要

近期用于优化提示词、程序和机器学习工作流的系统通常依赖显式的外层循环控制器，如进化搜索、多臂老虎机或文本梯度方法。我们提出了一个根本不同的问题：这种搜索策略中有多少可以被单个使用工具的智能体内化？我们提出ReASearch——一个统一的推理驱动优化框架，其中智能体自主决定评估什么、如何诊断失败、进行哪些修改，以及何时验证或重启。该智能体不仅仅是由手工设计的启发式规则引导的提议生成器，而是主动分析结果、分配预算，并通过持久记忆在长时间跨度内优化其策略。凭借共享的智能体循环和领域专用工具，ReASearch以完全相同的框架实例化来优化提示词、程序和机器学习工作流。在14项不同的任务中，它与专门的优化系统相比具有竞争力，且大多数情况下表现更优，相比强领域特定基线实现了2%至40%的提升，在某些情况下发现的解决方案甚至优于此前人类已知的最佳结果。关键的是，我们观察到通常由显式控制器实现的复杂搜索行为，会自然地从智能体的推理过程中涌现。

English

Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods. We ask a fundamentally different question: how much of this search policy can be internalized by a single tool-using agent? We present ReASearch, a unified framework for reasoning-driven optimization in which the agent autonomously decides what to evaluate, how to diagnose failures, which edits to make, and when to verify or restart. Rather than serving only as a proposal generator guided by hand-designed heuristics, the agent actively analyzes outcomes, allocates budget, and refines its strategy over long horizons through persistent memory. With a shared agent loop and domain-specific tools, ReASearch instantiates the exact same scaffold to optimize prompts, programs, and ML workflows. Across 14 diverse tasks, it is competitive with and mostly better than specialized optimization systems, achieving gains of 2% to 40% over strong domain-specific baselines, and in some cases discovering solutions that improve on prior human best-known results. Crucially, we observe that complex search behaviors, which are typically implemented by explicit controllers, emerge naturally from the agent's reasoning process.