跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20671 · v1

MASTA: A Feedback-Scheduled Multi-Agent System for End-to-End Tamarin Modeling and Analysis

首次提交 2026-11-16 15:33
版本更新 2026-11-16 15:33
雷达观测 2026-11-17 13:07
arXiv ↗PDF ↗

摘要

Tamarin-based formal verification of security protocols requires expert-authored multiset rewriting rules and temporal-logic lemmas. Translating a natural-language protocol description into a complete formal model with an LLM is hard because syntactic, reachability, and property-level errors compound across the multi-step modeling process, and a single agent that both authors and self-evaluates cannot reliably localize them. We present MASTA, a multi-agent system that addresses these difficulties through three innovations. First, an operational--evaluative role decomposition assigns rule modeling to an Architect, property modeling to an Auditor, and pure dispatch to a dedicated Arbiter that holds no authoring duties. Second, the Arbiter implements a Tamarin-anchored scheduler that dispatches the next agent based on the latest verifier verdict and routes problem-tagged fixes through a modification list, with a six-class problem taxonomy and an LLM deduplication check preventing routing deadlock. Third, we construct a benchmark of 10 protocols paired with 139 mutation variants and five fine-grained metrics that jointly assess model correctness (M1M_1--M3M_3) and completeness (M4M_4--M5M_5). On this benchmark, MASTA on Qwen 3.5-plus improves over OpenCode on the same backbone by up to +0.27+0.27 on individual metrics and ranks first on both the correctness and completeness averages, surpassing Codex (GPT-5.5) and Claude Code (Opus 4.7) despite using a weaker LLM. Ablations on five protocols confirm that removing the Arbiter collapses property and verification scores to zero.

作者备注:Accepted at NeurIPS 2026 (Main Track, poster). 19 pages

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

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

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。

v1 · 2026-11-16 15:33 · 最新观测版本

MASTA: A Feedback-Scheduled Multi-Agent System for End-to-End Tamarin Modeling and Analysis

Tamarin-based formal verification of security protocols requires expert-authored multiset rewriting rules and temporal-logic lemmas. Translating a natural-language protocol description into a complete formal model with an LLM is hard because syntactic, reachability, and property-level errors compound across the multi-step modeling process, and a single agent that both authors and self-evaluates cannot reliably localize them. We present MASTA, a multi-agent system that addresses these difficulties through three innovations. First, an operational--evaluative role decomposition assigns rule modeling to an Architect, property modeling to an Auditor, and pure dispatch to a dedicated Arbiter that holds no authoring duties. Second, the Arbiter implements a Tamarin-anchored scheduler that dispatches the next agent based on the latest verifier verdict and routes problem-tagged fixes through a modification list, with a six-class problem taxonomy and an LLM deduplication check preventing routing deadlock. Third, we construct a benchmark of 10 protocols paired with 139 mutation variants and five fine-grained metrics that jointly assess model correctness (M1M_1--M3M_3) and completeness (M4M_4--M5M_5). On this benchmark, MASTA on Qwen 3.5-plus improves over OpenCode on the same backbone by up to +0.27+0.27 on individual metrics and ranks first on both the correctness and completeness averages, surpassing Codex (GPT-5.5) and Claude Code (Opus 4.7) despite using a weaker LLM. Ablations on five protocols confirm that removing the Arbiter collapses property and verification scores to zero.

查看此版本解读 →查看此版本原文 ↗