In recent years, deep learning techniques have been developed to improve the performance of program synthesis from input-output examples. Albeit its significant progress, the programs that can be synthesized by state-of-the-art approaches are still simple in terms of their complexity. In this work, we move a significant step forward along this direction by proposing a new class of challenging tasks in the domain of program synthesis from input-output examples: learning a context-free parser from pairs of input programs and their parse trees. We show that this class of tasks are much more challenging than previously studied tasks, and the test accuracy of existing approaches is almost 0%.
We tackle the challenges by developing three novel techniques inspired by three novel observations, which reveal the key ingredients of using deep learning to synthesize a complex program. First, the use of a non-differentiable machine is the key to effectively restrict the search space. Thus our proposed approach learns a neural program operating a domain-specific non-differentiable machine. Second, recursion is the key to achieve generalizability. Thus, we bake-in the notion of recursion in the design of our non-differentiable machine. Third, reinforcement learning is the key to learn how to operate the non-differentiable machine, but it is also hard to train the model effectively with existing reinforcement learning algorithms from a cold boot. We develop a novel two-phase reinforcement learning-based search algorithm to overcome this issue. In our evaluation, we show that using our novel approach, neural parsing programs can be learned to achieve 100% test accuracy on test inputs that are 500x longer than the training samples.
Horn-ICE Learning for Synthesizing Invariants and Contracts
Indian Institute of Science(印度科学学院);Amazon India(亚马逊印度);University of Illinois, Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所)
VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search
Kempner Institute at Harvard University(哈佛大学肯普纳研究所);Harvard University(哈佛大学);TU München(慕尼黑工业大学);Northeastern University(东北大学);University of Alabama at Birmingham(阿拉巴马大学伯明翰分校);University of Oxford(牛津大学)
Controller Synthesis from Noisy-Input Noisy-Output Data
Engineering and Technology Institute, University of Groningen(格罗宁根大学工程与技术学院);Department of Electronics, Information, and Bioengineering, Politecnico di Milano(米兰理工学院电子、信息与生物工程系)