SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing

TL;DR

SPEAR introduces a multi-agent system for smart contract auditing, employing specialized agents and coordination protocols to enhance security analysis and recovery in a realistic workflow.

Contribution

The paper presents a novel multi-agent coordination framework for smart contract auditing, integrating established MAS patterns into a practical security analysis process.

Findings

Multi-agent design improves coordination and recovery over centralized approaches.

Agents effectively prioritize, allocate, and repair in security workflows.

Empirical results demonstrate resource efficiency and robustness in failure scenarios.

Abstract

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.