LLM-Guided Loop Bound Generation for Program Termination Verification
Zan Gong, Biting Huang, Fei He
2026年份
摘要
Program termination is a fundamental liveness property in software verification. Proving termination of a given program is a formidable challenge due to the undecidability of the problem. In this paper, we propose LIFT, a termination verification framework that leverages LLMs to generate loop bounds within a guess-and-check workflow. LIFT couples this generation with a sound formal validation procedure that both guarantees all reported terminations and refutes invalid loop bounds via violation analysis. Experiments on publicly accessible termination benchmarks show that LIFT significantly outperforms existing termination verification tools.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper5
- Can Large Language Models Reason about Program Invariants?Kexin Pei, David Bieber, Kensen Shi, Charles Sutton 等ICML 2023 · 被引用 128 次
- Enchanting Program Specification Synthesis by Large Language Models Using Static Analysis and Program VerificationCheng Wen, Jialun Cao, Jie Su, Zhiwu Xu 等CAV 2024 · 被引用 60 次
- Laurel: Unblocking Automated Verification with Large Language ModelsEric Mugnier, Emmanuel Anaya Gonzalez, Nadia Polikarpova, Ranjit Jhala 等OOPSLA 2025 · 被引用 12 次
- LLM Meets Bounded Model Checking: Neuro-symbolic Loop Invariant InferenceGuangyuan Wu, Weining Cao, Yuan Yao, Hengfeng Wei 等ASE 2024 · 被引用 9 次
- Clause2Inv: A Generate-Combine-Check Framework for Loop Invariant InferenceWeining Cao, Guangyuan Wu, Tangzhi Xu, Yuan Yao 等ISSTA 2025 · 被引用 2 次
相关 Paper
- Data-Driven Loop Bound Learning for Termination AnalysisRongchen Xu, Jianhui Chen, Fei HeICSE 2022 · 被引用 6 次
- Data-driven Recurrent Set Learning For Non-termination AnalysisZhilei Han, Fei HeICSE 2023 · 被引用 1 次
- Loop Invariant Inference through SMT Solving Enhanced Reinforcement LearningShiwen Yu, Ting Wang, Ji WangISSTA 2023 · 被引用 11 次
- Lemur: Integrating Large Language Models in Automated Program VerificationHaoze Wu, Clark W. Barrett, Nina NarodytskaICLR 2024 · 被引用 67 次
- LLM-Generated Invariants for Bounded Model Checking Without Loop UnrollingMuhammad A. A. Pirzada, Giles Reger, Ahmed Bhayat, Lucas C. CordeiroASE 2024 · 被引用 7 次
