跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2605.10005 · v3

Hybrid Mechanical and Agentic Specification Inference

首次提交 2026-05-11 13:30
版本更新 2026-11-13 08:53
雷达观测 2026-11-17 04:57
arXiv ↗PDF ↗

摘要

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.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-13 08:53 · 最新观测版本

Hybrid Mechanical and Agentic Specification Inference

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.

查看此版本解读 →查看此版本原文 ↗