跳到正文
arXiv cs.MA· Gerhard Yu (Alex), Amanuel Aknaw (Alex), Amir Ali Mohaghegh (Alex), Yong Song (Alex), Cao, Alvine B. Belle·· 9 小时前AI 评分31

eTrustWare:受法庭启发的多智能体 LLM 框架,自动生成安全案例

The Defense Rests: A Courtroom-Inspired Multi-Agent LLM Framework for Automated Safety Case Generation

AI 导读

研究者提出 eTrustWare,一个基于 LLM 的多智能体框架,用于自动生成与审查安全案例。该框架将安全案例构建类比为法庭审判:安全分析师担任"检察官"识别危害,安全论证开发者担任"辩护律师"构建论证,编排者担任"法官"协调交互,评审委员会担任"陪审团"评估论证完整性与说服力。在多个 ML 赋能的自动驾驶系统安全案例上的实验表明,协调式 LLM 智能体生成安全案例具备可行性。

正文 · 原文

View PDF HTML (experimental)

Abstract:Safety cases are widely used to demonstrate that mission-critical systems, such as autonomous vehicles and unmanned aerial systems, can operate safely after deployment. However, manually constructing safety cases is complex, time-consuming, and labor-intensive, which calls for the proposal of automated approaches to support their creation. Inspired by the legal nature of safety case construction, we formalize the safety case creation problem through a courtroom analogy, where stakeholders collaboratively propose, examine, criticize, review, improve and validate safety claims and their supporting evidence. In this analogy, the safety analyst acts as a prosecutor by identifying hazards and safety concerns, while the assurance case developer serves as a defense attorney by constructing and substantiating safety arguments. An orchestrator acts as a judge by coordinating stakeholder interactions, and a review board serves as a jury by assessing argument completeness and persuasiveness. Based on this formalization, we propose eTrustWare, a Large Language Model (LLM)-based multi-agent framework for automated safety case generation and review. Our experiments on several safety cases of ML-enabled autonomous driving systems demonstrate the feasibility of coordinated LLM-based agents for generating safety cases.
Comments: 10 pages
Subjects: Software Engineering (cs.SE); Multiagent Systems (cs.MA)
Cite as: arXiv:2611.21618 [cs.SE]
  (or arXiv:2611.21618v1 [cs.SE] for this version)
  https://doi.org/10.48550/arXiv.2611.21618

arXiv-issued DOI via DataCite

Submission history

From: Alvine B. Belle [view email]
[v1] Wed, 2 Sep 2026 03:02:12 UTC (102 KB)

来源:arXiv cs.MA · arxiv.org