SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
This work addresses smart contract auditing for security analysis, presenting an incremental engineering case study.
The paper tackles smart contract auditing by introducing SPEAR, a multi-agent coordination framework that applies established multi-agent system patterns to model auditing as a coordinated mission with specialized agents, resulting in an empirical study comparing it to centralized and pipeline-based alternatives under controlled failure scenarios.
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.