GAE：通过强化优化实现科学发现的图增强进化
GAE: Graph-Augmented Evolution for Scientific Discovery via Reinforcement Optimization
浏览论文内容
中文总结 AI 辅助
针对大语言模型引导的进化程序搜索的瓶颈，提出GAE框架，通过图神经网络、强化学习优化的元控制器和在线微调循环解决问题，在复杂非线性振荡器系统符号回归任务中有效发现物理方程，性能达最优。
中文摘要 AI 辅助
由大语言模型（LLMs）引导的进化程序搜索已成为自动科学发现的强大范式。然而，当前方法存在三个瓶颈：结构盲的亲本选择、稀疏的全程序评估奖励以及搜索过程中无法自适应的静态变异算子。我们提出GAE（图增强进化）框架，通过紧密耦合的三支柱架构解决这些限制。首先，关系图神经网络将程序解析为类型化计算图，生成结构感知嵌入。其次，基于强化学习优化的元控制器利用这些嵌入，通过定向策略取代盲进化采样，根据奖励历史动态选择最优亲本和变异方向。第三，在线GRPO微调循环在测试时使用组归一化评估奖励持续更新LLM变异算子，使模型生成分布与高适应性结构编辑直接对齐。我们在具有挑战性的科学发现任务——复杂非线性振荡器系统的符号回归上评估GAE。通过将随机搜索转化为定向、自我改进的轨迹，GAE有效地发现了闭式物理方程，始终匹配或优于静态LLM驱动的基线，并实现了分布外的最优性能。
英文摘要
Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery. However, current approaches are fundamentally constrained by three bottlenecks: structurally blind parent selection, sparse whole-program evaluation rewards, and static mutation operators that fail to adapt during search. We present GAE (Graph-Augmented Evolution), a framework that resolves these limitations through a tightly coupled, three-pillar architecture. First, a relational graph neural network (GNN) parses programs into typed computation graphs, producing structure-aware embeddings. Second, an RL-optimized meta-controller leverages these embeddings to replace blind evolutionary sampling with a directed policy, dynamically selecting optimal parents and mutation directions based on reward history. Third, an online GRPO fine-tuning loop continuously updates the LLM mutation operator at test-time using group-normalized evaluation rewards, directly aligning the model's generation distribution with high-fitness structural edits. We evaluate GAE on a challenging scientific discovery task: symbolic regression for complex nonlinear oscillator systems. By transforming stochastic search into a directed, self-improving trajectory, GAE efficiently discovers closed-form physical equations, consistently matching or outperforming static LLM-driven baselines and achieving state-of-the-art out-of-distribution performance.
