Akıllı Kontrat Geliştirme Süreçlerinde Yapay Zekanın Rolü: Kapsamlı ve Sistematik Bir Literatür Taraması

Abstract

Blockchain teknolojisinin temelini oluşturan akıllı kontratlar, dijital anlaşmaların otomasyonunda bir devrim vaat etmektedir. Ancak bu potansiyel, ciddi güvenlik açıkları, yüksek geliştirme maliyetleri ve performans verimsizlikleri gibi önemli zorluklarla gölgelenmektedir. Bu sistematik literatür taraması, yapay zeka (AI) ve makine öğrenmesi (ML) teknolojilerinin, akıllı kontrat yaşam döngüsünün her aşamasında bu zorlukları ele almak için nasıl giderek daha merkezi bir rol oynadığını derinlemesine incelemektedir. 50’den fazla hakemli akademik makale, konferans bildirisi ve endüstri raporu analiz edilerek, AI’nın akıllı kontrat geliştirme süreçlerindeki uygulamaları dört ana tematik eksende incelenmiştir: (1) Güvenlik Açığı Tespiti ve Analizi, (2) Kod Üretimi ve Otomasyon, (3) Performans Optimizasyonu ve Gaz Maliyeti Azaltma, ve (4) Ekosistem Entegrasyonu ve Sektörel Uygulamalar. Bulgularımız, özellikle Transformer tabanlı modeller (örneğin, CodeBERT) ve Büyük Dil Modelleri (LLM’ler) gibi ileri AI tekniklerinin, statik analiz araçlarının sınırlamalarını aşarak güvenlik açığı tespitinde %99’a varan doğruluk oranları sunduğunu ortaya koymaktadır. Ayrıca, LLM’lerin doğal dilden otomatik olarak güvenli ve verimli Solidity kodu üretme yeteneği, geliştirme paradigmalarını temelden değiştirme potansiyeli taşımaktadır. Bu çalışma, mevcut metodolojileri, kullanılan veri setlerini ve elde edilen performans metriklerini karşılaştırmalı tablolarla sunmakta, alandaki temel evrimsel eğilimleri (2018’den günümüze) analiz etmekte, önemli araştırma boşluklarını (örneğin, açıklanabilirlik, repository- level anlayış) belirlemekte ve gelecekteki araştırma yönelimleri için somut öneriler sunmaktadır. Bu kapsamlı analiz hem akademik araştırmacılar hem de endüstri profesyonelleri için mevcut durumu ve gelecekteki potansiyeli aydınlatan temel bir kaynak olmayı amaçlamaktadır.

Keywords

• Akıllı kontratlar
• Blockchain
• Güvenlik açığı tespiti
• Kod otomasyonu
• Yapay zekâ

The Role of Artificial Intelligence in Smart Contract Development Processes: A Comprehensive and Systematic Literature Review

Abstract

Smart contracts, which form the foundation of blockchain technology, promise a revolution in the automation of digital agreements. However, this potential is overshadowed by significant challenges such as serious security vulnerabilities, high development costs, and performance inefficiencies. This systematic literature review provides an in-depth examination of how artificial intelligence (AI) and machine learning (ML) technologies are playing an increasingly central role in addressing these challenges at every stage of the smart contract lifecycle. By analyzing more than 50 peer-reviewed academic papers, conference proceedings, and industry reports, the applications of AI in smart contract development processes are investigated along four main thematic axes: (1) Vulnerability Detection and Analysis, (2) Code Generation and Automation, (3) Performance Optimization and Gas Cost Reduction, and (4) Ecosystem Integration and Sectoral Applications. Our findings reveal that advanced AI techniques, particularly Transformer-based models (e.g., CodeBERT) and Large Language Models (LLMs), offer up to 99% accuracy in vulnerability detection, surpassing the limitations of traditional static analysis tools. Furthermore, the ability of LLMs to automatically generate secure and efficient Solidity code from natural language holds the potential to fundamentally transform development paradigms. This study presents comparative tables summarizing existing methodologies, datasets, and performance metrics, analyzes key evolutionary trends in the field (from 2018 to the present), identifies major research gaps (e.g., explainability, repository-level understanding), and provides concrete recommendations for future research directions. Through this comprehensive analysis, the study aims to serve as a fundamental resource illuminating both the current state and future potential of the field for academic researchers and industry professionals alike.

Keywords

• Artificial intelligence
• Blockchain
• Code automation
• Smart contracts
• Vulnerability detection

References

1. [1] N. Szabo, "Smart contracts: Building blocks for digital markets," EXTROPY: The Journal of Transhumanist Thought, vol. 18, no. 2, p. 28, 1996.
2. [2] J. Li, Z. Zhao, Z. Su, and W. Meng, "Gas-expensive patterns detection to optimize smart contracts," Applied Soft Computing, vol. 145, p. 110542, 2023.
3. [3] A. Laurent, L. Brotcorne, and B. Fortz, "Transaction fees optimization in the Ethereum blockchain," Blockchain: Research and Applications, vol. 3, no. 3, p. 100074, 2022.
4. [4] X. Tang, Y. Du, A. Lai, Z. Zhang, and L. Shi, "Deep learning-based solution for smart contract vulnerabilities detection," Scientific Reports, vol. 13, no. 1, p. 20106, 2023.
5. [5] P. Momeni, Y. Wang, and R. Samavi, "Machine learning model for smart contracts security analysis," in Proc. 17th Int. Conf. Privacy, Security Trust (PST), 2019, pp. 1–6.
6. [6] J. Crisostomo, F. Bacao, and V. Lobo, "Machine learning methods for detecting smart contracts vulnerabilities within Ethereum blockchain—A review," Expert Systems With Applications, vol. 268, p. 126353, 2025.
7. [7] Y. Huang, J. Li, S. Fang, Y. Li, P. Yang, and B. Hu, "Smart contract intent detection with pre-trained programming language model," arXiv preprint arXiv:2508.20086, 2025.
8. [8] Z. Feng, D. Guo, D. Tang, N. Duan, X. Feng, M. Gong, L. Shou, B. Qin, T. Liu, D. Jiang, and S. Zhou, "CodeBERT: A pre-trained model for programming and natural languages," in Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, pp. 1536–1547.

9. [9] P. Xu, X. Zhu, and D. A. Clifton, "Multimodal learning with transformers: A survey," IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 10, pp. 12113–12132, 2023.
10. [10] W. Jie, Q. Chen, J. Wang, A. S. V. Koe, J. Li, P. Huang, Y. Wu, and Y. Wang, "A novel extended multimodal AI framework towards vulnerability detection in smart contracts," Information Sciences, vol. 636, p. 118907, 2023.
11. [11] W. Deng, H. Wei, T. Huang, C. Cao, Y. Peng, and X. Hu, "Smart contract vulnerability detection based on deep learning and multimodal decision fusion," Sensors, vol. 23, no. 16, p. 7246, 2023.
12. [12] P. Tolmach, Y. Li, S.-W. Lin, Y. Liu, and Z. Li, "A survey of smart contract formal specification and verification," ACM Computing Surveys, vol. 54, no. 7, pp. 1–38, 2021. [13] Y. Murray and D. A. Anisi, "Survey of formal verification methods for smart contracts on blockchain," in Proc. 10th IFIP Int. Conf. New Technologies, Mobility Security (NTMS), 2019, pp. 1–6.
13. [14] S. Chen and F. Li, "Ponzi scheme detection in smart contracts using the integration of deep learning and formal verification," IET Blockchain, vol. 4, no. 2, pp. 185–196, 2024.
14. [15] Z. Guo, "Blockchain-enhanced smart contracts for formal verification of IoT access control mechanisms," Alexandria Engineering Journal, vol. 118, pp. 315–324, 2025.
15. [16] A. Gervais and L. Zhou, "AI agent smart contract exploit generation," arXiv preprint arXiv:2507.05558, 2025.
16. [17] Z. Peng, X. Yin, R. Qian, P. Lin, Y. Liu, H. Zhang, C. Ying, and Y. Luo, "SolEval: Benchmarking large language models for repository-level Solidity code generation," arXiv preprint arXiv:2502.18793, 2025.
17. [18] G. De Vito, D. D'Amici, F. Izzo, F. Ferrucci, and D. Di Nucci, "LLM-based generation of Solidity smart contracts from system requirements in natural language: The AstraKode case," in Proc. IEEE Int. Conf. Softw. Analysis, Evolution Reengineering (SANER), 2025, pp. 170–180.
18. [19] E. A. Napoli, N. Romani, V. Gatteschi, and C. Schifanella, "Light and shadows of smart contract development with LLMs," Expert Systems With Applications, p. 129011, 2025.
19. [20] Z. He, Z. Li, S. Yang, H. Ye, A. Qiao, X. Zhang, X. Luo, and T. Chen, "Large language models for blockchain security: A systematic literature review," arXiv preprint arXiv:2403.14280, 2024.
20. [21] S. Khalid and C. Brown, "Evaluating capabilities and perspectives of generative AI tools in smart contract development," in Proc. 7th ACM Int. Symp. Blockchain Secure Critical Infrastructure, 2025, pp. 1–12.
21. [22] "ChainGPT AI Smart-Contract Generator," ChainGPT Documentation, 2025. [Online]. Available: https://docs.chaingpt.org/ai-tools-and-applications/ai-smart-contract-generator
22. [23] "ContractGPT: AI Tool Fine-Tuned by CodeBERT for Smart Contract Development," HackQuest Project, 2025. [Online]. Available: https://www.hackquest.io/es/projects/contractgpt
23. [24] "Workik Smart Contract Generator," Workik, 2025. [Online]. Available: https://workik.com/smart-contract-generator
24. [25] J. Zhao, X. Chen, G. Yang, and Y. Shen, "Automatic smart contract comment generation via large language models and in-context learning," Information and Software Technology, vol. 168, p. 107405, 2024.
25. [26] S.-J. Hwang, S. H. Ju, and Y.-H. Choi, "CGGNet: Compiler-guided generation network for smart contract data augmentation," IEEE Access, vol. 12, pp. 97515–97532, 2024. A. Laurent, L. Brotcorne, and B. Fortz, "Transaction fees optimization in the Ethereum blockchain," Blockchain: Research and Applications, vol. 3, no. 3, p. 100074, 2022.
26. [27] "Optimizing Ethereum Gas Fees Using Machine Learning," ResearchGate, 2025. [Online]. Available: https://www.researchgate.net/publication/3887912 91_Optimizing_Ethereum_Gas_Fees_Using_Mach ine_Learning_A_Predictive_and_Adaptive_Appro ach
27. [28] S. Khanzadeh, N. Samreen, and M. H. Alalfi, "Optimizing gas consumption in Ethereum smart contracts: Best practices and techniques," in Proc. IEEE 23rd Int. Conf. Softw. Quality, Reliability, Security Companion (QRS-C), 2023, pp. 300–309.
28. [29] Q.-P. Kong, Z.-Y. Wang, Y. Huang, X.-P. Chen, X.-C. Zhou, Z.-B. Zheng, and G. Huang, "Characterizing and detecting gas-inefficient patterns in smart contracts," J. Comput. Sci. Technol., vol. 37, no. 1, pp. 67–82, 2022.
29. [30] J. Zheng, Z. Peng, Y. Liu, J. Wang, Y. Liao, W. Dong, and X. He, "GasAgent: A multi-agent framework for automated gas optimization in smart contracts," arXiv preprint arXiv:2507.15761, 2025.
30. [31] S. Misbah, M. F. Shahid, S. Siddiqui, T. J. S. Khanzada, R. B. Ashari, Z. Ullah, and M. Jamjoom, "Generative AI-driven smart contract optimization for secure and scalable smart city services," Smart Cities, vol. 8, no. 4, p. 118, 2025.
31. [32] A. Manimuthu, V. G. Venkatesh, Y. Shi, V. R. Sreedharan, and S. C. L. Koh, "Design and development of automobile assembly model using federated artificial intelligence with smart contract," Int. J. Production Research, vol. 60, no. 1, pp. 111–135, 2022.
32. [33] S. M. Rahim, Z. Z. Mohamad, J. A. Bakar, F. H. Mohsin, and N. M. Isa, "Artificial intelligence, smart contract and Islamic finance," Asian Social Science, vol. 14, no. 2, p. 145, 2018.
33. [34] [S. Ouf, S. Ahmed, and Y. Helmy, "A blockchain based deep learning framework for a smart learning environment," Scientific Reports, vol. 15, no. 1, p. 19519, 2025.
34. [35] B. D. Deebak and F. AL-Turjman, "Privacy-preserving in smart contracts using blockchain and artificial intelligence for cyber risk measurements," J. Inf. Security Appl., vol. 58, p. 102749, 2021.
35. [36] X. Zeng, Y. Xian, D. Xuan, D. Yang, C. Li, J. Chen, P. Fan, and P. Liu, "Connecting large language models with blockchain: Making smart contracts smarter," ACM Trans. Web, vol. 20, no. 1, pp. 1–21, 2026.