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.

翻译：本文提出SPEAR——一种用于智能合约审计的多智能体协同框架，该框架将既有的多智能体系统模式应用于真实安全分析流程。SPEAR将审计建模为由专业化智能体协同完成的任务：规划智能体基于风险感知启发式策略确定合约优先级，执行智能体通过合同网协议分配任务，修复智能体采用程序优先的修复策略自主恢复脆弱的生成产物。各智能体通过符合AGM公理体系的知识修正机制维护局部信念，借助协商与拍卖协议进行协同，并在获取新信息时动态调整计划。实证研究在可控故障场景下将多智能体设计方案与集中式及流水线式替代方案进行对比，重点分析协同行为、恢复机制与资源利用效率。