EUVIMEDEUVIMED entdecken
Crossref

AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents

Yiyi Lu, Hoi Ian Au, Junyao Zhang, Jingyu Pan, Guanglei Zhou, Yiting Wang, Jingwei Sun, Ang Li, Jianyi Zhang, Hai Li, Yiran Chen

ACM Transactions on Design Automation of Electronic Systems · 20.08.2026

DOI: 10.1145/3842675 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 20.08.2026. Verfasst von Yiyi Lu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electronic Design Automation (EDA) remains heavily reliant on tool command language (Tcl) scripting to drive complex RTL-to-GDSII flows. This scripting-based paradigm is labor-intensive, error-prone, and difficult to scale across large design projects. Recent advances in large language models (LLMs) suggest a new paradigm of natural language–driven automation. However, existing EDA efforts remain limited and face key challenges, including the absence of standardized interaction protocols and dependence on external APIs that introduce privacy risks. We present AutoEDA , a framework that leverages the Model Context Protocol (MCP) to support natural-language construction and execution of evaluated RTL-to-GDSII design flows. AutoEDA combines a locally fine-tuned intent-to-IR client with stage-level MCP tools and deterministic server procedures for validation, template rendering, artifact management, execution, and report collection. We further contribute a benchmark generation pipeline for diverse EDA scenarios and extend CodeBLEU with Tcl-specific enhancements for domain-aware script-fidelity evaluation. Empirical results show that AutoEDA achieves up to 9.9 × higher CodeBLEU than the direct-generation baseline while reducing token usage by approximately 97% compared with in-context learning. Our evaluation focuses on the reliability layer of natural-language EDA automation: generating executable Tcl flows that preserve stage dependencies and produce reports for downstream timing, area, power, and routing analysis. It does not claim closed-loop QoR optimization or industrial sign-off quality.

Zitieren

APA

Lu, Y., Au, H. I., Zhang, J., Pan, J., Zhou, G., Wang, Y., Sun, J., Li, A., Zhang, J., Li, H., & Chen, Y. (2026). AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents. ACM Transactions on Design Automation of Electronic Systems. https://doi.org/10.1145/3842675

Vancouver

Lu Y, Au HI, Zhang J, Pan J, Zhou G, Wang Y, et al. AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents. ACM Transactions on Design Automation of Electronic Systems. 2026. doi:10.1145/3842675

BibTeX
@article{Lu2026,
  author = {Lu, Yiyi and Au, Hoi Ian and Zhang, Junyao and Pan, Jingyu and Zhou, Guanglei and Wang, Yiting and Sun, Jingwei and Li, Ang and Zhang, Jianyi and Li, Hai and Chen, Yiran},
  title = {AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2026},
  doi = {10.1145/3842675}
}
Kostenlos starten →