代码进化用于控制：通过LLM驱动的进化搜索合成策略
Code Evolution for Control: Synthesizing Policies via LLM-Driven Evolutionary Search
AI总结：
本文提出利用LLM驱动的进化搜索生成可解释的控制策略，通过代码进化方法合成可执行代码，提升自主系统控制策略的可解释性和可靠性。
摘要：
为自主系统设计有效的控制策略仍然是一个根本性挑战，传统上通过强化学习或手动工程来解决。虽然强化学习取得了显著成功，但往往面临样本复杂性高、奖励塑造困难以及产生难以解释或验证的神经网络策略的问题。手动设计需要大量领域专业知识，并且在跨多样任务扩展时遇到困难。在本工作中，我们证明LLM驱动的进化搜索可以有效地合成可解释的控制策略，形式为可执行代码。通过将策略合成视为代码进化问题，我们利用LLM对编程模式和控制启发法的先验知识，同时采用进化搜索系统地探索解决方案空间。我们使用EvoToolkit框架实现我们的方法，该框架无缝整合LLM驱动的进化与可定制的适应度评估。我们的方法通过迭代进化候选策略程序的种群，评估它们与任务特定目标的匹配程度，并选择表现更好的个体进行繁殖。这一过程产生紧凑、可读的控制策略，可以直接检查、修改和形式验证。本工作突显了结合基础模型与进化计算在自主系统中合成可信控制策略的潜力。代码可在https://github.com/pgg3/EvoControl获取。
英文摘要：
Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it often suffers from high sample complexity, reward shaping difficulties, and produces opaque neural network policies that are hard to interpret or verify. Manual design, on the other hand, requires substantial domain expertise and struggles to scale across diverse tasks. In this work, we demonstrate that LLM-driven evolutionary search can effectively synthesize interpretable control policies in the form of executable code. By treating policy synthesis as a code evolution problem, we harness the LLM's prior knowledge of programming patterns and control heuristics while employing evolutionary search to explore the solution space systematically. We implement our approach using EvoToolkit, a framework that seamlessly integrates LLM-driven evolution with customizable fitness evaluation. Our method iteratively evolves populations of candidate policy programs, evaluating them against task-specific objectives and selecting superior individuals for reproduction. This process yields compact, human-readable control policies that can be directly inspected, modified, and formally verified. This work highlights the potential of combining foundation models with evolutionary computation for synthesizing trustworthy control policies in autonomous systems. Code is available at https://github.com/pgg3/EvoControl.
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。
