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

• URL: http://arxiv.org/abs/2511.12164v1
• Date: Sat, 15 Nov 2025 11:21:56 GMT
• Title: Multi-Agent Collaborative Fuzzing with Continuous Reflection for Smart Contracts Vulnerability Detection
• Authors: Jie Chen, Liangmin Wang,
• Abstract summary: SmartFuzz is a novel collaborative reflective fuzzer for smart contract vulnerability detection.<n>It employs large language model-driven agents as the fuzzing engine and continuously improves itself by learning and reflecting.<n>It detects 5.8%-74.7% more vulnerabilities within 30 minutes, and (ii) it reduces false negatives by up to 80%.
• Score: 16.160978409552182
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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\%.

Related papers

• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks [62.031889234230725]
  6G networks rely on complex cross-layer optimization.<n> manually translating high-level intents into mathematical formulations remains a bottleneck.<n>We present ComAgent, a multi-LLM agentic AI framework.
  arXiv  Detail & Related papers  (2026-01-27T13:43:59Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Trace: Securing Smart Contract Repository Against Access Control Vulnerability [58.02691083789239]
  GitHub hosts numerous smart contract repositories containing source code, documentation, and configuration files.<n>Third-party developers often reference, reuse, or fork code from these repositories during custom development.<n>Existing tools for detecting smart contract vulnerabilities are limited in their ability to handle complex repositories.
  arXiv  Detail & Related papers  (2025-10-22T05:18:28Z)
• Generic Adversarial Smart Contract Detection with Semantics and Uncertainty-Aware LLM [18.01454017110476]
  FinDet is a generic adversarial smart contracts detection framework.<n>It takes as input only the EVM-bytecode contracts and identifies adversarial ones with high balanced accuracy.<n>Our comprehensive evaluation shows that FinDet achieves a BAC of 0.9223 and a TPR of 0.8950, significantly outperforming existing baselines.
  arXiv  Detail & Related papers  (2025-09-23T12:52:05Z)
• LLAMA: Multi-Feedback Smart Contract Fuzzing Framework with LLM-Guided Seed Generation [56.84049855266145]
  We propose a Multi-feedback Smart Contract Fuzzing framework (LLAMA) that integrates evolutionary mutation strategies, and hybrid testing techniques.<n>LLAMA achieves 91% instruction coverage and 90% branch coverage, while detecting 132 out of 148 known vulnerabilities.<n>These results highlight LLAMA's effectiveness, adaptability, and practicality in real-world smart contract security testing scenarios.
  arXiv  Detail & Related papers  (2025-07-16T09:46:58Z)
• CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems [55.57181090183713]
  We introduce CoTGuard, a novel framework for copyright protection that leverages trigger-based detection within Chain-of-Thought reasoning.<n>Specifically, we can activate specific CoT segments and monitor intermediate reasoning steps for unauthorized content reproduction by embedding specific trigger queries into agent prompts.<n>This approach enables fine-grained, interpretable detection of copyright violations in collaborative agent scenarios.
  arXiv  Detail & Related papers  (2025-05-26T01:42:37Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• ContractTrace: Retracing Smart Contract Versions for Security Analyses [4.126275271359132]
  We introduce ContractTrace, an automated infrastructure that accurately identifies and links versions of smart contracts into coherent lineages.<n>This capability is essential for understanding vulnerability propagation patterns and evaluating the effectiveness of security patches in blockchain environments.
  arXiv  Detail & Related papers  (2024-12-30T11:10:22Z)
• SmartOracle: Generating Smart Contract Oracle via Fine-Grained Invariant Detection [27.4175374482506]
  SmartOracle is a dynamic invariant detector that automatically generates fine-grained invariants as application-specific oracles for vulnerability detection. From historical transactions, SmartOracle uses pattern-based detection and advanced inference to construct comprehensive properties. SmartOracle successfully detects 466 abnormal transactions with an acceptable precision rate 96%, involving 31 vulnerable contracts.
  arXiv  Detail & Related papers  (2024-06-14T14:09:20Z)
• Efficiently Detecting Reentrancy Vulnerabilities in Complex Smart Contracts [35.26195628798847]
  Existing vulnerability detection tools perform poorly in terms of efficiency and successful detection rates for vulnerabilities in complex contracts. SliSE provides a robust and efficient method for detection of Reentrancy vulnerabilities for complex contracts.
  arXiv  Detail & Related papers  (2024-03-17T16:08:30Z)
• LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts [15.071155232677643]
  Decentralized Finance (DeFi) has resulted in financial losses exceeding 3 billion US dollars.<n>Current detection tools face significant challenges in identifying attack activities effectively.<n>We propose LookAhead, a new framework for detecting DeFi attacks via unveiling adversarial contracts.
  arXiv  Detail & Related papers  (2024-01-14T11:39:33Z)
• Enhancing Smart Contract Security Analysis with Execution Property Graphs [48.31617821205042]
  We introduce Clue, a dynamic analysis framework specifically designed for a runtime virtual machine.<n>Clue captures critical information during contract executions, employing a novel graph-based representation, the Execution Property Graph.<n> evaluation results reveal Clue's superior performance with high true positive rates and low false positive rates, outperforming state-of-the-art tools.
  arXiv  Detail & Related papers  (2023-05-23T13:16:42Z)
• ESCORT: Ethereum Smart COntRacTs Vulnerability Detection using Deep Neural Network and Transfer Learning [80.85273827468063]
  Existing machine learning-based vulnerability detection methods are limited and only inspect whether the smart contract is vulnerable. We propose ESCORT, the first Deep Neural Network (DNN)-based vulnerability detection framework for smart contracts. We show that ESCORT achieves an average F1-score of 95% on six vulnerability types and the detection time is 0.02 seconds per contract.
  arXiv  Detail & Related papers  (2021-03-23T15:04:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.