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

arXiv: https://arxiv.org/abs/2602.04418 · HTML: https://mlsanity.com/paper/2602.04418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 37 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019)
- [GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis](https://mlsanity.com/paper/2308.03314/) (2023)
- [SoK: Decentralized Finance (DeFi)](https://mlsanity.com/paper/2101.08778/) (2021)
- [SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework](https://mlsanity.com/paper/2411.19234/) (2024)
- [Generative Large Language Model usage in Smart Contract Vulnerability Detection](https://mlsanity.com/paper/2504.04685/) (2025)
- [Smart Contract Repair](https://mlsanity.com/paper/1912.05823/) (2019)
- [Adaptive Plan-Execute Framework for Smart Contract Security Auditing](https://mlsanity.com/paper/2505.15242/) (2025)
- [A Multi-Agent Framework for Testing Distributed Systems](https://mlsanity.com/paper/1512.00313/) (2015)

## Abstract (arXiv)

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.