用多智能体协作提升智能合约审计的鲁棒性与效率
SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
- 设计三类专用智能体分工协作：规划、执行、修复
- 在故障场景下相比单体和流水线方案，协调成功率提升37%
- 适合安全审计系统研发者及区块链平台构建者参考
我们提出SPEAR，一个用于智能合约审计的多智能体协同框架，将成熟的多智能体系统（MAS）模式应用于真实的安全分析流程。SPEAR将审计建模为由专业智能体协同完成的任务：规划智能体使用风险感知启发式方法优先处理合约，执行智能体通过合约网协议分配任务，修复智能体则采用程序化优先的修复策略自动恢复脆弱生成物。各智能体通过符合AGM规范的信念更新机制维护本地认知，利用协商与拍卖协议进行协调，并在获取新信息时动态调整计划。一项实证研究在受控故障场景下对比了多智能体设计与集中式及流水线式替代方案，重点评估协调能力、恢复行为与资源利用率。
原文摘要 · Abstract (English)
We present SPEAR, a multi-agent coordination framework for smart contract auditing that applies established MAS patterns in a realistic security analysis workflow. SPEAR models auditing as a coordinated mission carried out by specialized agents: a Planning Agent prioritizes contracts using risk-aware heuristics, an Execution Agent allocates tasks via the Contract Net protocol, and a Repair Agent autonomously recovers from brittle generated artifacts using a programmatic-first repair policy. Agents maintain local beliefs updated through AGM-compliant revision, coordinate via negotiation and auction protocols, and revise plans as new information becomes available. An empirical study compares the multi-agent design with centralized and pipeline-based alternatives under controlled failure scenarios, focusing on coordination, recovery behavior, and resource use.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。