Guangyuan Wu

Guangyuan Wu

Auto-generated profile, based on publicly available information

Guangyuan Wu

Nanjing University, Nanjing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 October 2024
Verified
Conference Paper
Open access
GWGuangyuan Wu
Guangyuan Wu
WCWeining Cao
Weining Cao
YYYuan Yao
Yuan Yao
HWHengfeng Wei
Hengfeng Wei
TCTaolue Chen
Taolue Chen
XMXiaoxing Ma
Xiaoxing Ma
Loop invariant inference, a key component in program verification, is a challenging task due to the inherent undecidability and complex loop behaviors in practice. Recently, machine learning based techniques have demonstrated impressive performance in generating loop invariants automatically. However, these methods highly rely on the labeled training data, and are intrinsically random and uncertain, leading to unstable performance. In this paper, we investigate a synergy of large language models (LLMs) and bounded model checking (BMC) to address these issues. The key observation is that, although LLMs may not be able to return the correct loop invariant in one response, they usually can provide all individual predicates of the correct loop invariant in multiple responses. To this end, we propose a "query-filter-reassemble" strategy, namely, we first leverage the language generation power of LLMs to produce a set of candidate invariants, where training data is not needed. Then, we employ BMC to identify valid predicates from these candidate invariants, which are assembled to produce new candidate invariants and checked by off-the-shelf SMT solvers. The feedback is incorporated into the prompt for the next round of LLM querying. We expand the existing benchmark of 133 programs to 316 programs, providing a more comprehensive testing ground. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art techniques, successfully generating 309 loop invariants out of 316 cases, whereas the existing baseline methods are only able to tackle 219 programs at best. The code is publicly available at https://github.com/SoftWiser-group/LaM4Inv.git.

22 June 2025 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
WCWeining Cao
Weining Cao
GWGuangyuan Wu
Guangyuan Wu
TXTangzhi Xu
Tangzhi Xu
YYYuan Yao
Yuan Yao
HWHengfeng Wei
Hengfeng Wei
XMXiaoxing Ma
Xiaoxing Ma
Loop invariant inference is a fundamental, yet challenging, problem in program verification. Recent work adopts the guess-and-check framework, where candidate loop invariants are iteratively generated in the guess step and verified in the check step. A major challenge of this general framework is to produce high-quality candidate invariants in each iteration so that the inference procedure can converge quickly. Empirically, we observe that existing approaches may struggle with guessing the complete invariant due to the complexity of logical connectives, but usually, all the clauses of the correct loop invariant have already appeared in the previous guesses. This motivates us to refine the guess-and-check framework, resulting in a generate-combine-check framework, where the loop invariant inference task is divided into clause generation and clause combination. Specifically, we propose a novel loop invariant inference approach under the new framework, which consists of an LLM-based clause generator and a counterexample-driven clause combinator. As the clause generator, leverages LLMs to generate a multitude of clauses; as the clause combinator, leverages counterexamples from the previous rounds to convert generated clauses into invariants. Our experiments show that significantly outperforms existing loop invariant inference approaches. For example, solved 312 (out of 316) linear invariant inference tasks and 44 (out of 50) nonlinear invariant inference tasks, which is at least 93 and 16 more than the existing baselines, respectively. By design, the generate-combine-check framework is flexible to accommodate various existing approaches which are currently under the guess-and-check framework by splitting the guessed candidate invariants into clauses. The evaluation shows that our approach can, with minor adaptation, improve existing loop invariant inference approaches in both effectiveness and efficiency. For example, Code2Inv which solved 210 linear problems with an average solving time of 137.6 seconds can be improved to solve 252 problems with an average solving time of 17.8 seconds.

17 April 2022
Verified
Book Chapter
Closed access
PDF file
XHXiaomeng Han
Xiaomeng Han
YRYijie Ren
Yijie Ren
YWYibo Wang
Yibo Wang
JWJinze Wang
Jinze Wang
YXYifan Xiong
Yifan Xiong
XLXiaozhou Li
Xiaozhou Li

1 August 2021 in Tehnicki vjesnik - Technical Gazette
Verified
Journal Article
Open access
PDF file
XLXiaozhou Li
Xiaozhou Li
XHXiaomeng Han
Xiaomeng Han
JLJingjing Liu
Jingjing Liu
XLXuelin Li
Xuelin Li
MCMingming Cui
Mingming Cui
GWGuangyuan Wu
Guangyuan Wu
The overall appearance perception is affected by luminance perception accuracy and efficiency mostly. The surface luminance prediction correlated with surface angle and surface tone value was performed by measuring and modeling the paper...

28 September 2026
Verified
Conference Paper
Open access
WCWeining Cao
Weining Cao
GWGuangyuan Wu
Guangyuan Wu
YYYuan Yao
Yuan Yao
HWHengfeng Wei
Hengfeng Wei
TCTaolue Chen
Taolue Chen
XMXiaoxing Ma
Xiaoxing Ma