AI RESEARCH
SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
arXiv CS.AI
•
ArXi:2602.04418v3 Announce Type: replace-cross 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.