Search is an important technique in program synthesis that allows for adaptive strategies such as focusing on particular search directions based on execution results. Several prior works have demonstrated that neural models are effective at guiding program synthesis searches. However, a common drawback of those approaches is the inability to handle iterative loops, higher-order functions, or lambda functions, thus limiting prior neural searches from synthesizing longer and more general programs. We address this gap by designing a search algorithm called LambdaBeam that can construct arbitrary lambda functions that compose operations within a given DSL. We create semantic vector representations of the execution behavior of the lambda functions and train a neural policy network to choose which lambdas to construct during search, and pass them as arguments to higher-order functions to perform looping computations. Our experiments show that LambdaBeam outperforms neural, symbolic, and LLM-based techniques in an integer list manipulation domain.

设计了一种搜索算法LambdaBeam，在DSL中构建任意Lambda函数的语义向量表示，并训练神经策略网络，将它们作为参数传递给高阶函数进行循环计算，相比基于神经网络、符号和LLM的技术，在整数列表操作领域性能更优。

LambdaBeam：使用高阶函数和Lambda进行神经程序搜索