collaborators

5 papers

cs.SE2026

How Powerful are LLMs in Generating Formal Program Specifications?

Fanpeng Yang, Xing Li, Shuling Wang +7

Formal verification provides strong guarantees of software correctness, but its adoption is limited by the high cost of writing precise formal specifications. While recent large la…

cs.SE2026

KBSpec: LLM-driven Formal Specification Generation with Evolving Domain Knowledge Base

Wenhan Wang, Zeyu Sun

Automated formal specification generation is a key step towards program understanding and formal verification. Recently, due to the success of large language models (LLMs) in code…

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.SE2025

Can Large Language Models Reason About Complex Execution Paths? An Empirical Study on Python

Wenhan Wang, Kaibo Liu, Zeyu Sun +4

Execution path reasoning is a key step towards program semantics understanding. It is crucial for generating test cases that cover certain branches/paths, or detecting bugs that ar…

cs.SE2025

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR

Zeyu Sun, Jingjing Liang, Weiyi Wang +3

MLIR (Multi-Level Intermediate Representation) has rapidly become a foundational technology for modern compiler frameworks, enabling extensibility across diverse domains. However,…