2 papers
cs.SE2026
SpecRL: Reinforcement Learning with Test-Based Completeness Rewards for Formal Specification Synthesis
Zhechong Huang, Zhao Zhang, Zeyu Sun +2
Specification synthesis asks a model to generate specifications and auxiliary annotations for an existing program. In modern software verification projects, specification accuracy…
cs.PL2025
Learning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis
Zhechong Huang, Zhao Zhang, Ruyi Ji +6
Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such as constrained…