Lune

ASE2025Top-tier venue

Agentic Specification Generator for Move Programs

Yu-Fu Fu, Meng Xu, Taesoo Kim

Abstract

While LLM-based specification generation is gaining traction, existing tools primarily focus on mainstream programming languages like C, Java, and even Solidity, leaving emerging and yet verification-oriented languages like Move underexplored. In this paper, we introduce Msg, an automated specification generation tool designed for Move smart contracts. Msg aims to highlight key insights that uniquely present when applying LLM-based specification generation to a new ecosystem. Specifically, Msg demonstrates that LLMs exhibit robust code comprehension and generation capabilities even for non-mainstream languages. Msg successfully generates verifiable specifications for 84% of tested Move functions and even identifies clauses previously overlooked by experts. Additionally, Msg shows that explicitly leveraging specification language features through an agentic, modular design improves specification quality substantially (generating 57% more verifiable clauses than conventional designs). Incorporating feedback from the verification toolchain further enhances the effectiveness of Msg, leading to a 30% increase in generated verifiable specifications.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • A Tale of 1001 LoC: Potential Runtime Error-Guided Specification Synthesis for Verifying Large-Scale Programs cites Enchanting Program Specification Synthesis by Large Language Models Using Static Analysis and Program Verification
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. A Tale of 1001 LoC: Potential Runtime Error-Guided Specification Synthesis for Verifying Large-Scale ProgramsZhongyi Wang, Tengjie Lin, Mingshuai Chen, Haokun Li et al.OOPSLA 2026 · 1 citation

Builds on11

  1. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  2. Repository-Level Prompt Generation for Large Language Models of CodeDisha Shrivastava, Hugo Larochelle, Daniel TarlowICML 2023 · 184 citations
  3. GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program AnalysisYuqiang Sun, Daoyuan Wu, Yue Xue, Han Liu et al.ICSE 2024 · 131 citations
  4. Enchanting Program Specification Synthesis by Large Language Models Using Static Analysis and Program VerificationCheng Wen, Jialun Cao, Jie Su, Zhiwu Xu et al.CAV 2024 · 60 citations
  5. Ranking LLM-Generated Loop Invariants for Program VerificationSaikat Chakraborty, Shuvendu K. Lahiri, Sarah Fakhoury, Akash Lal et al.EMNLP Findings 2023 · 36 citations

Related papers

  1. Belobog: Move Language Fuzzing Framework for Real-World Smart ContractsZiqiao Kong, Wanxu Xia, Zhengwei Li, Yi Lu et al.ISSTA 2026
  2. SpecGen: Automated Generation of Formal Program Specifications via Large Language ModelsLezhi Ma, Shangqing Liu, Yi Li, Xiaofei Xie et al.ICSE 2025 · 25 citations
  3. Verifying Declarative Smart ContractsHaoxian Chen, Lan Lu, Brendan Massey, Yuepeng Wang et al.ICSE 2024 · 2 citations
  4. PrefGen: A Preference-Driven Methodology for Secure Yet Gas-Efficient Smart Contract GenerationZhiyuan Peng, Xin Yin, Zijie Zhou, Chenhao Ying et al.ASE 2025 · 3 citations
  5. VeriExploit: Automatic Bug Reproduction in Smart Contracts via LLMs and Formal MethodsChenfeng Wei, Shiyu Cai, Yiannis Charalambous, Tong Wu et al.ASE 2025
Dusk over the sea between two cliffs drawn in fine vertical lines