机械与智能体混合的规格推断方法,助力 Move 形式化验证
Hybrid Mechanical and Agentic Specification Inference
AI 导读
一项研究提出面向 Move 智能合约语言的机械与智能体混合规格推断方法,集成进 Move Prover 验证器,由 LLM 智能体通过调用 Move Prover 并基于最弱前置条件(WP)分析从代码推导规格。
正文 · 原文
Abstract:Adoption of formal verification has long been hindered by the cost of manual specification. To prove high-level properties, one must also write contracts for supporting functions, many of which are mechanical and low-level. Specification inference automatically derives such contracts from the program. We present a hybrid of mechanical and agentic inference for Move, a smart contract language, integrated into its verifier, the Move Prover. A large language model (LLM) agent drives inference and verification through a tool that calls the Move Prover and derives specifications from code by weakest-precondition (WP) analysis. We evaluate our approach on 26 targets, 24 of them extracted from public Move functions of the Aptos framework that have no specifications, under a frontier model and a mid-tier model of the same family (Sol 5.6 and Terra 5.6). With and without WP, the agent completes over 90% of its runs, so agentic inference is effective on its own. Adding WP lowers its cost by 11-21% overall and by 40-64% on targets without loops.
| Subjects: | Programming Languages (cs.PL); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Software Engineering (cs.SE) |
| MSC classes: | 68Q60, 68V15, 68T20 |
| ACM classes: | F.3.1; D.2.4; I.2.2 |
| Cite as: | arXiv:2605.10005 [cs.PL] |
| (or arXiv:2605.10005v3 [cs.PL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10005 arXiv-issued DOI via DataCite |
Submission history
From: Wolfgang Grieskamp [view email]
[v1]
Mon, 11 May 2026 05:30:25 UTC (27 KB)
[v2]
Wed, 13 May 2026 02:35:58 UTC (27 KB)
[v3]
Fri, 13 Nov 2026 00:53:58 UTC (54 KB)
来源:arXiv cs.AI · arxiv.org