LLM Agents as Catalysts for Resilient DFT: An Orchestration-Based Framework Beyond Brittle Scripts
Source abstract
Abstract
As the complexity of Very-Large-Scale Integration (VLSI) circuits escalates, Design-for-Test (DFT) faces significant challenges. Traditional script-based automation flows are increasingly complex and present a high technical barrier for non-specialists. In order to overcome the above issue, this paper introduces DFTAgent, a novel framework that leverages Large Language Models to intelligently orchestrate a DFT toolchain. DFTAgent is evaluated on the ISCAS’85, ISCAS’89, and ITC’99 benchmarks. The results demonstrate that DFTAgent successfully completes the complete ATPG task cycle, achieving fault coverage comparable to a manually scripted baseline while exhibiting significant advantages in flexibility and error handling. By abstracting complex DFT tools behind a natural language interface and a visual workflow, this approach promises to democratize access to advanced VLSI testing methodologies and accelerate design cycles.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Innovative Microfluidic and Catalytic Techniques Innovation · Security and Verification in Computing · Semiconductor materials and devices
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, China
University of Chinese Academy of Sciences, Beijing 101408, China
Guangdong Greater Bay Area Institute of Integrated Circuits and Systems, Guangzhou 510530, China
Funding
National Natural Science Foundation of China
References (27)
Show source-provided references
1. Agnihotri, P., Kalla, P., and Blair, S. (2024, January 3–8). Design-for-Test for Silicon Photonic Circuits. Proceedings of the 2024 IEEE International Test Conference (ITC), San Diego, CA, USA.10.1109/ITC51657.2024.00025 ↗
2. Yuan, S., Yaldagard, M.A., Xun, H., Fieback, M., Marinissen, E.J., Kim, W., Rao, S., Couet, S., Taouil, M., and Hamdioui, S. (2024, January 20–24). Design-for-test for intermittent faults in STT-MRAMs. Proceedings of the 2024 IEEE European Test Symposium (ETS), The Hague, The Netherlands.10.1109/ETS61313.2024.10567702 ↗
3. Improving test automation maturity: A multivocal literature review10.1002/stvr.1804 ↗
4. Testing research software: An in-depth survey of practices, methods, and tools10.1007/s10664-025-10620-6 ↗
5. A survey of research in large language models for electronic design automation
6. Pasandi, G., Kunal, K., Tej, V., Shan, K., Sun, H., Jain, S., Li, C., Deng, C., Ene, T.D., and Ren, H. (2025). JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation. arXiv.
7. Machine learning for electronic design automation: A survey10.1145/3451179 ↗
8. A graph placement methodology for fast chip design10.1038/s41586-021-03544-w ↗
9. Shi, Z., Li, M., Khan, S., Wang, L., Wang, N., Huang, Y., and Xu, Q. (2022, January 23–30). Deeptpi: Test point insertion with deep reinforcement learning. Proceedings of the 2022 IEEE International Test Conference (ITC), Anaheim, CA, USA.10.1109/ITC50671.2022.00027 ↗
10. Chen, Z., Xu, J., Alippi, C., Ding, S.X., Shardt, Y., Peng, T., and Yang, C. (2021). Graph neural network-based fault diagnosis: A review. arXiv.
11. Pandey, S., and Sarangi, S.R. (2024, January 22–25). HybMT: Hybrid Meta-Predictor based ML Algorithm for Fast Test Vector Generation. Proceedings of the 2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC), Incheon, Republic of Korea.10.1109/ASP-DAC58780.2024.10473922 ↗
12. Banerjee, S., Talukdar, J., and Firouzi, F. (2025, January 4–6). Silicon Whisperers: Improving Test Quality and Cost in the Age of Generative AI. Proceedings of the 2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS), Madison, WI, USA.10.1109/COINS65080.2025.11125741 ↗
13. Chen, L., Chen, Y., Chu, Z., Fang, W., Ho, T.Y., Huang, R., Huang, Y., Khan, S., Li, M., and Li, X. (2024). The dawn of ai-native eda: Opportunities and challenges of large circuit models. arXiv.
14. Large circuit models: Opportunities and challenges10.1007/s11432-024-4155-7 ↗
15. Huang, Z., Huang, Z., Tao, S., Chen, S., Zeng, Z., Ni, L., Zhuang, C., Li, W., Zhao, X., and Liu, H. (2024, January 10–13). AiEDA: An open-source AI-native EDA library. Proceedings of the 2024 2nd International Symposium of Electronics Design Automation (ISEDA), Xi’an, China.10.1109/ISEDA62518.2024.10617562 ↗
16. Verigen: A large language model for verilog code generation10.1145/3643681 ↗
17. Firouzi, F., Nakkilla, S.S.R., Fu, C., Banerjee, S., Talukdar, J., and Chakrabarty, K. (2024, January 27–31). Llm-aid: Leveraging large language models for rapid domain-specific accelerator development. Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, New York, NY, USA.10.1145/3676536.3697135 ↗
18. Fu, Y., Zhang, Y., Yu, Z., Li, S., Ye, Z., Li, C., Wan, C., and Lin, Y.C. (November, January 28). Gpt4aigchip: Towards next-generation ai accelerator design automation via large language models. Proceedings of the 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD), San Francisco, CA, USA.10.1109/ICCAD57390.2023.10323953 ↗
19. Chateda: A large language model powered autonomous agent for eda10.1109/TCAD.2024.3383347 ↗
20. Jiang, Z., Zhang, Q., Liu, C., Cheng, L., Li, H., and Li, X. (2024). Iicpilot: An intelligent integrated circuit backend design framework using open eda. arXiv.
21. Wu, H., Zheng, H., He, Z., and Yu, B. (2025). Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation. arXiv.10.18653/v1/2025.naacl-long.83 ↗
22. Wang, X., Wan, G.W., Wong, S.Z., Zhang, L., Liu, T., Tian, Q., and Ye, J. (2024, January 23–27). Chatcpu: An agile cpu design and verification platform with llm. Proceedings of the 61st ACM/IEEE Design Automation Conference, San Francisco, CA, USA.10.1145/3649329.3658493 ↗
23. Hu, Y., Ye, J., Xu, K., Sun, J., Zhang, S., Jiao, X., Pan, D., Zhou, J., Wang, N., and Shan, W. (2024). Uvllm: An automated universal rtl verification framework using llms. arXiv.
24. LayoutCopilot: An LLM-Powered Multiagent Collaborative Framework for Interactive Analog Layout Design10.1109/TCAD.2025.3529805 ↗
25. Petrolo, V., Medya, S., Graziano, M., and Pal, D. (2024, January 12–14). DETECTive: Machine Learning-driven Automatic Test Pattern Prediction for Faults in Digital Circuits. Proceedings of the Great Lakes Symposium on VLSI 2024, GLSVLSI ’24, Clearwater, FL, USA.10.1145/3649476.3658696 ↗
26. Shrestha, P., Aversa, A., Phatharodom, S., and Savidis, I. (2024, January 12–14). EDA-schema: A Graph Datamodel Schema and Open Dataset for Digital Design Automation. Proceedings of the Great Lakes Symposium on VLSI 2024, GLSVLSI ’24, Clearwater, FL, USA.10.1145/3649476.3658718 ↗
27. Deep transfer learning approach for digital circuits vulnerability analysis10.1016/j.eswa.2023.121757 ↗