arXiv 2605.138212026-05-13cs.AIcs.LG

利用代理进化

Harnessing Agentic Evolution

The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；DeepWisdom；Singapore University of Technology and Design（新加坡科技设计大学）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；Université de Montréal & Mila（蒙特利尔大学及Mila）

Jiayi Zhang, Yongfeng Gu, Jianhao Ruan, Maojia Song, Yiran Peng, Zhiguang Han, Jinyu Xiang, Zhitao Wang, Caiyin Yang, Yixi Ouyang, Bang Liu, Chenglin Wu, Yuyu Luo

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出AEvo框架，通过统一接口整合程序和代理进化，提升长周期搜索性能，在多个基准测试中优于现有方法。

摘要：

代理进化作为一种强大的范式，通过迭代生成候选方案、评估并利用反馈来指导未来的搜索过程，从而改进程序、工作流和科学解决方案。然而，现有方法通常被实例化为固定的手工设计过程，这些过程模块化但僵化，或者为通用代理，能够灵活整合反馈，但在长周期进化中容易漂移。两者在时间积累丰富的证据，包括候选方案、反馈、轨迹和失败，但缺乏一个稳定的接口来组织这些证据并修订驱动未来进化的机制。我们通过将代理进化制定为一个交互式环境来解决这一限制，其中积累的进化上下文作为过程级状态。我们引入了AEvo，一个被利用的元编辑框架，其中元代理观察到这个状态，并不直接提出下一个候选方案，而是编辑控制未来进化的过程或代理上下文。这种统一的接口使AEvo能够引导基于过程和基于代理的进化，使积累的证据对长周期搜索具有作用。在代理和推理基准测试中，AEvo的实证评估显示，AEvo在五个进化基线中表现更优，相对于最强基线实现了26%的相对改进。在三个开放性优化任务中，AEvo进一步优于四个进化基线，并在相同迭代预算下实现了最先进的性能。

英文摘要：

Agentic evolution has emerged as a powerful paradigm for improving programs, workflows, and scientific solutions by iteratively generating candidates, evaluating them, and using feedback to guide future search. However, existing methods are typically instantiated either as fixed hand-designed procedures that are modular but rigid, or as general-purpose agents that flexibly integrate feedback but can drift in long-horizon evolution. Both forms accumulate rich evidence over time, including candidates, feedback, traces, and failures, yet lack a stable interface for organizing this evidence and revising the mechanism that drives future evolution. We address this limitation by formulating agentic evolution as an interactive environment, where the accumulated evolution context serves as a process-level state. We introduce AEvo, a harnessed meta-editing framework in which a meta-agent observes this state and acts not by directly proposing the next candidate, but by editing the procedure or agent context that controls future evolution. This unified interface enables AEvo to steer both procedure-based and agent-based evolution, making accumulated evidence actionable for long-horizon search. Empirical evaluations on agentic and reasoning benchmarks show that AEvo outperforms five evolution baselines, achieving a 26 relative improvement over the strongest baseline. Across three open-ended optimization tasks, AEvo further outperforms four evolution baselines and achieves state-of-the-art performance under the same iteration budget.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。