EcoSearch: A Constant-Delay Best-First Search Algorithm for Program Synthesis
원문 초록
Many approaches to program synthesis perform a combinatorial search within a large space of programs to find one that satisfies a given specification. To tame the search space blowup, previous works introduced probabilistic and neural approaches to guide this combinatorial search by inducing heuristic cost functions. Best-first search algorithms ensure to search in the exact order induced by the cost function, significantly reducing the portion of the program space to be explored. We present a new best-first search algorithm called EcoSearch, which is the first constant-delay algorithm for pre-generation cost function: the amount of compute required between outputting two programs is constant, and in particular does not increase over time. This key property yields important speedups: we observe that EcoSearch outperforms its predecessors on two classic domains.
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.