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

Engineering notes

Engineering notes will be added by the aipentium editorial team.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为大语言模型、生成式AI、ChatGPT相关技术、计算机视觉、深度学习等高价值论文补充中文说明。

Original abstract

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.

Links and sources

Comments