arXiv:2211.11937
Genetic Algorithm for Program Synthesis
원문 초록
A deductive program synthesis tool takes a specification as input and derives a program that satisfies the specification. The drawback of this approach is that search spaces for such correct programs tend to be enormous, making it difficult to derive correct programs within a realistic timeout. To speed up such program derivation, we improve the search strategy of a deductive program synthesis tool, SuSLik, using evolutionary computation. Our cross-validation shows that the improvement brought by evolutionary computation generalises to unforeseen problems.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CLEVER: A Curated Benchmark for Formally Verified Code Generation
Transductively Informed Inductive Program Synthesis
PoE-World: Compositional World Modeling with Products of Programmatic Experts
Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.