# Multi-Agent Collaborative Fuzzing with Continuous Reflection for Smart Contracts Vulnerability Detection

arXiv: https://arxiv.org/abs/2511.12164 · HTML: https://mlsanity.com/paper/2511.12164/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 15 of 15)

- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019)
- [Manticore: A User-Friendly Symbolic Execution Framework for Binaries and Smart Contracts](https://mlsanity.com/paper/1907.03890/) (2019)
- [Empirical Review of Automated Analysis Tools on 47,587 Ethereum Smart Contracts](https://mlsanity.com/paper/1910.10601/) (2019)
- [ContractFuzzer: Fuzzing Smart Contracts for Vulnerability Detection](https://mlsanity.com/paper/1807.03932/) (2018)
- [SoK: Decentralized Finance (DeFi) Attacks](https://mlsanity.com/paper/2208.13035/) (2022)
- [Learn&Fuzz: Machine Learning for Input Fuzzing](https://mlsanity.com/paper/1701.07232/) (2017)
- [NEUZZ: Efficient Fuzzing with Neural Program Smoothing](https://mlsanity.com/paper/1807.05620/) (2018)
- [sFuzz: An Efficient Adaptive Fuzzer for Solidity Smart Contracts](https://mlsanity.com/paper/2004.08563/) (2020)
- [SAILFISH: Vetting Smart Contract State-Inconsistency Bugs in Seconds](https://mlsanity.com/paper/2104.08638/) (2021)
- [DAppSCAN: Building Large-Scale Datasets for Smart Contract Weaknesses in DApp Projects](https://mlsanity.com/paper/2305.08456/) (2023)
- [DEFECTCHECKER: Automated Smart Contract Defect Detection by Analyzing EVM Bytecode](https://mlsanity.com/paper/2009.02663/) (2020)
- [EthIR: A Framework for High-Level Analysis of Ethereum Bytecode](https://mlsanity.com/paper/1805.07208/) (2018)
- [MuFuzz: Sequence-Aware Mutation and Seed Mask Guidance for Blockchain Smart Contract Fuzzing](https://mlsanity.com/paper/2312.04512/) (2023)
- [ConCert: A Smart Contract Certification Framework in Coq](https://mlsanity.com/paper/1907.10674/) (2019)

## Abstract (arXiv)

Fuzzing is a widely used technique for detecting vulnerabilities in smart contracts, which generates transaction sequences to explore the execution paths of smart contracts. However, existing fuzzers are falling short in detecting sophisticated vulnerabilities that require specific attack transaction sequences with proper inputs to trigger, as they (i) prioritize code coverage over vulnerability discovery, wasting considerable effort on non-vulnerable code regions, and (ii) lack semantic understanding of stateful contracts, generating numerous invalid transaction sequences that cannot pass runtime execution. In this paper, we propose SmartFuzz, a novel collaborative reflective fuzzer for smart contract vulnerability detection. It employs large language model-driven agents as the fuzzing engine and continuously improves itself by learning and reflecting through interactions with the environment. Specifically, we first propose a new Continuous Reflection Process (CRP) for fuzzing smart contracts, which reforms the transaction sequence generation as a self-evolving process through continuous reflection on feedback from the runtime environment. Then, we present the Reactive Collaborative Chain (RCC) to orchestrate the fuzzing process into multiple sub-tasks based on the dependencies of transaction sequences. Furthermore, we design a multi-agent collaborative team, where each expert agent is guided by the RCC to jointly generate and refine transaction sequences from both global and local perspectives. We conduct extensive experiments to evaluate SmartFuzz's performance on real-world contracts and DApp projects. The results demonstrate that SmartFuzz outperforms existing state-of-the-art tools: (i) it detects 5.8%-74.7% more vulnerabilities within 30 minutes, and (ii) it reduces false negatives by up to 80%.