LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
This addresses a bottleneck in program synthesis for developers by enabling more complex program generation, though it is incremental as it builds on prior neural-guided search methods.
The paper tackles the problem of neural program synthesis being unable to handle iterative loops, higher-order functions, or lambda functions, which limits the synthesis of longer and more general programs. The result is LambdaBeam, a search algorithm that outperforms neural, symbolic, and LLM-based techniques in an integer list manipulation domain.
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.