Large multimodal language models (LLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic policies. However, existing frameworks rely on a monolithic model call to simultaneously interpret visual behavioral evidence and synthesize corrective code. This diagnosis-repair entanglement creates an opaque feedback loop, obscuring the rationale behind mutations and preventing the retention of algorithmic insights across independent runs. To achieve auditable and efficient policy search, we argue that visual diagnosis must be structurally decoupled from code generation. We present REFLEX, a train-free evolutionary framework that operationalizes this decoupling. In REFLEX, a vision-enabled Critic first distills task-specific behavioral evidence into structured, auditable diagnoses. Subsequently, a text-optimized Actor synthesizes child policies using these diagnoses alongside a persistent, self-evolving Skill Memory of reusable code snippets. This architecture not only provides transparent mutation traces but also enables cross-run programmatic knowledge transfer. Extensive evaluations across control benchmarks (Lunar Lander, Acrobot, Pendulum) and a 36-dimensional antenna array synthesis task demonstrate exceptional sample efficiency. Notably, REFLEX solves Acrobot and Pendulum in under 10 LLM calls and reaches a best Normalized Weighted Score of 1.092 on Lunar Lander, achieving highly competitive final performance while significantly accelerating the early-stage discovery of transparent policies.

翻译：大型多模态语言模型已成为一种强大工具，可引导进化搜索生成可解释的程序化策略。然而，现有框架依赖于单一模型调用来同时解释视觉行为证据并合成修正代码。这种诊断-修复的耦合形成了一个不透明的反馈循环，掩盖了突变背后的原理，并阻止了跨独立运行保留算法洞察。为了实现可审计且高效的策略搜索，我们认为视觉诊断必须在结构上与代码生成解耦。我们提出REFLEX，一种无需训练的进化框架，实现了这种解耦。在REFLEX中，具备视觉能力的评论者首先将特定任务的行为证据蒸馏为结构化、可审计的诊断结果。随后，文本优化的执行者利用这些诊断结果以及一个持续自我演进的技能记忆库（包含可重用代码片段）合成子代策略。这种架构不仅提供了透明的突变轨迹，还实现了跨运行的程序化知识迁移。在控制基准任务（月球着陆器、Acrobot、倒立摆）和一个36维天线阵列合成任务上的广泛评估表明，该方法具有卓越的样本效率。值得注意的是，REFLEX在不到10次LLM调用中解决了Acrobot和倒立摆问题，并在月球着陆器上达到了最佳归一化加权分数1.092，在显著加速透明策略早期发现的同时，实现了极具竞争力的最终性能。