Blockagents: Towards byzantine-robust llm-based multi-agent coordination via blockchain
Open accessAbstract
Recent advancements in multi-agent systems based on large language models (LLM) have shown potential for problem-solving and planning tasks. However, most existing LLM-based multi-agent approaches show vulnerability against byzantine attacks. First, agents instantiated on diverse LLMs may inherit biases present in the LLMs and thus exhibit deception behavior. Second, as the number of agents grows, collusive behavior among multiple malicious agents poses a potential threat. In this paper, we propose BlockAgents, an innovative framework that integrates blockchain into LLM-based cooperative multi-agent systems to mitigate byzantine behaviors. BlockAgents completes multi-agent collaboration through a unified workflow including role assignment, proposal statement, evaluation, and decision-making. To help the agent who contributes the most to the group thinking process acquire accounting rights, we propose a proof-of-thought (PoT) consensus mechanism combined with stake-based miner designation and multi-round debate-style voting. To effectively distinguish valid and abnormal answers, we design a multi-metric prompt-based evaluation method for each evaluator to score each proposal by carefully and comprehensively considering multiple dimensions. Experiments on three datasets show that BlockAgents reduces the interference of poisoning attacks on accuracy to less than 3% and reduces the success rate of backdoor attacks to less than 5%, demonstrating the resistance ability against Byza…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Most existing multi-agent systems lack robustness.
“Most existing multi-agent systems lack robustness (Chen et al., 2024a;Zhang et al., 2024;He et al., 2025).”
From Free-MAD: Consensus-Free Multi-Agent Debate (2026) · cites this paper as Chen et al., 2024a
Cites
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187 · see citing works
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., & Zhu, C. (2023) · arXiv · doi:10.48550/arxiv.2303.16634 · Cited by 948 · see citing works
Network Embedding With Completely-Imbalanced Labels
Wang, Z., Ye, X., Wang, C., Cui, J., & Yu, P. S. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2971490 · Cited by 68 · see citing works
Self-citationPreserving Edge Knowledge Sharing Among IoT Services: A Blockchain-Based Approach
Li, G., Dong, M., Yang, L. T., Ota, K., Wu, J., & Li, J. (2020) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2019.2952587 · Cited by 66 · see citing works
Self-citationReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
Chen, J., Saha, S., & Bansal, M. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.381 · Cited by 64 · see citing works
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
Souri, H., Fowl, L. H., Chellappa, R., Goldblum, M., & Goldstein, T. (2022) · neural information processing systems · doi:10.52202/068431-1393 · Cited by 57 · see citing works
PoisonPrompt: Backdoor Attack on Prompt-Based Large Language Models
Yao, H., Lou, J., & Qin, Z. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446267 · Cited by 51 · see citing works
Defending Against Poisoning Attacks in Federated Learning With Blockchain
Dong, N., Wang, Z., Sun, J., Kampffmeyer, M., Knottenbelt, W. J., & Xing, E. P. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3376651 · Cited by 47 · see citing works
Self-citationZero-shot Node Classification with Decomposed Graph Prototype Network
Wang, Z., Wang, J., Guo, Y., & Gong, Z. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467230 · Cited by 41 · see citing works
Self-citationOn the Exploitability of Instruction Tuning
Shu, M., Wang, J., Zhu, C., Geiping, J., Xiao, C., & Goldstein, T. (2023) · neural information processing systems · doi:10.52202/075280-2703 · Cited by 28 · see citing works
Generative AI for Software Security Analysis: Fundamentals, Applications, and Challenges
Ding, A., Li, G., Yi, X., Lin, X., Li, J., & Zhang, C. (2024) · IEEE Software · doi:10.1109/ms.2024.3416036 · Cited by 21 · see citing works
Self-citationFLoBC: A Decentralized Blockchain-Based Federated Learning Framework
Ghanem, M. C., Dawoud, F., Gamal, H., Soliman, E., ElBatt, T., & Sharara, H. (2022) · International Conference on Blockchain Computing and Applications (BCCA) · doi:10.1109/bcca55292.2022.9922258 · Cited by 17 · see citing works
PBE-Plan: Periodic Backdoor Erasing Plan for Trustworthy Federated Learning
Chen, B., Li, G., Chen, M., Liu, Y., Yi, X., & Li, J. (2023) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys60770.2023.00016 · Cited by 2 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
AI Agents Meet Blockchain: A Survey on Secure and Scalable Collaboration for Multi-Agents
Karim, M. M., Van, D. H., Khan, S., Qu, Q., & Kholodov, Y. A. (2025) · Future Internet · doi:10.3390/fi17020057 · Cited by 78 · see citing works
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
Yu, M., Meng, F., Zhou, X., Wang, S., Mao, J., Pan, L., Chen, T., Wang, K., Li, X., Zhang, Y., et al. (2025) · Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · doi:10.1145/3711896.3736561 · Cited by 34 · see citing works
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
Yu, M., Meng, F., Zhou, X., Wang, S., Mao, J., Pang, L., Chen, T., Wang, K., Li, X., Zhang, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.09648 · Cited by 34 · see citing works
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
Chhabra, A., Datta, S., Nahin, S. K., & Mohapatra, P. (2026) · IEEE Access · doi:10.1109/access.2026.3675554 · Cited by 28 · see citing works
“We also delineate potential shortcomings of these approaches.”
Li, A., Wong, P. K.-Y., Tao, X., Ma, J., & Cheng, J. C. P. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103375 · Cited by 20 · see citing works
A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network
Luo, H., Sun, G., Liu, Y., Zhao, D., Niyato, D., Yu, H., & Dustdar, S. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3620286 · Cited by 12 · see citing works
Qi, M.-F., Zhu, T.-Q., Zhang, L.-F., Li, N.-R., Tan, Y.-A., & Zhou, W.-L. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3659486 · Cited by 5 · see citing works
Free-MAD: Consensus-Free Multi-Agent Debate
Cui, Y., Fu, H., Zhang, H., Wang, L., & Zuo, C. (2026) · Findings of the Association for Computational Linguistics: ACL 2026 · doi:10.18653/v1/2026.findings-acl.1600 · Cited by 3 · see citing works
Revisão Sistemática da Literatura integrando Sistemas Multiagente e Large Language Models
Born, M. B., Alves, B. C., Goulart, F. M., Caldas, L. B., & de Aguiar, M. S. (2025) · Anais do Workshop-Escola de Sistemas de Agentes, seus Ambientes e Aplicações (WESAAC) · doi:10.5753/wesaac.2025.37538 · Cited by 1 · see citing works
Authenticated and Offline-Verifiable Agent-to-Agent Messaging for LLM Agents
Alshammari, A., Assiri, S., & Bahşi, H. (2026) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc67433.2026.11393740 · Cited by 1 · see citing works
Hossen, M. S., Jahan, T., Barua, A., & Opel, M. Z. K. (2025) · 2025 IEEE 4th International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON) · doi:10.1109/raaicon69033.2025.11502408
SoK: The Attack Surface of Agentic AI - Tools and Autonomy
Dehghantanha, A., & Homayoun, S. (2026) · arXiv · doi:10.48550/arxiv.2603.22928
Securing Agentic AI with the NIST Cybersecurity Framework 2.0
Metin, B., Karaca, H. S., Iradat, F., & Wynn, M. G. (2025) · National Conference on Electrical and Electronics Engineering (ELECO) · doi:10.1109/eleco69582.2025.11329370
Vanmala, & Dubey, A. K. (2025) · International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN) · doi:10.1109/icrcicn68210.2025.11364831
A Blockchain-Based AIGC Review Mechanism
Zhu, H., & Zhang, Q. (2026) · Mechanisms and machine science · doi:10.1007/978-3-032-17313-3_30
Robust LLM-based Multi-Agent System with Action Negotiation and Sharing Redundancy Enhancement
Li, X., Cui, B., Huang, J., & Chen, L. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780202
Li, Z., Wen, J., Liao, J., Jin, X., Miao, X., Pan, G., Zhong, W., Xie, S., & Kim, D. I. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3731984
Alhwikem, F., Khan, A. R., & Jaskani, F. H. (2026) · Symmetry · doi:10.3390/sym18091565
Towards Secure and Auditable Agentic AI Using Blockchain: A Review and Taxonomy
Bouhassoune, K., Goundar, S., & Haqiq, A. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-18758-1_22
BAg-IDS: A Blockchain-Enabled Agentic AI Architecture for Trustworthy Intrusion DetectionPreprint
BAHRI, M. A. E., Jemili, F., & MOSBAH, M. (2026) · Research Square · doi:10.21203/rs.3.rs-10843028/v1
- Authors
- Chen, B., Li, G., Lin, X., Wang, Z., & Li, J.
- Affiliations
- Shanghai Jiao Tong University (CN)
- Venue
- ACM Turing Award Celebration Conference 2024
- Publisher
- ACM
- Published
- 2024-07-05
- Pages
- 187-192
- OpenAlex
- W4401105851
- Cited by
- 15
- References
- 11
- Citations by year
- 2026: 7 · 2025: 8
- FWCI
- 5.71
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Turing Celebration Conference - China (ACM TURC) (publishedVersion, cc-by)
- Funders
- National Nature Science Foundation of China (U21B2019, U20B2048, 62202303)
- curity CommunicNational Key Laboratory of Seation Foundation (6142103042310)
- Topics
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Keywords
- multi-agent LLM systems, blockchain, Byzantine attacks, prompt-based evaluation, poisoning attacks, backdoor attacks, collusive behavior, deception, role assignment, decision-making
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
