SP
BravenNow
AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents
| USA | technology | ✓ Verified - arxiv.org

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

#AutoEDA #Electronic Design Automation #LLM agents #Microservices #Natural language control #RTL-to-GDSII flows #Model Context Protocol #Tcl scripting

📌 Key Takeaways

  • AutoEDA enables end-to-end natural language control of chip design flows
  • The framework uses microservice-based LLM agents to overcome limitations of traditional Tcl scripting
  • AutoEDA introduces MCP-based servers for task decomposition, tool selection, and error handling
  • The system achieves up to 9.9 times higher accuracy than naive approaches
  • Token usage is reduced by approximately 97% compared to in-context learning

📖 Full Retelling

Empirical testing of the AutoEDA framework demonstrated significant performance improvements over existing approaches, with results showing up to 9.9 times higher accuracy than naive implementations and approximately 97% reduction in token usage compared to traditional in-context learning methods. This efficiency gain represents a substantial advancement in making EDA workflows more accessible to engineers while maintaining the precision required for semiconductor design. The framework's ability to understand and execute complex design instructions through natural language interaction has the potential to democratize access to advanced EDA tools, reduce the learning curve for new designers, and accelerate the overall chip design process. As semiconductor complexity continues to increase according to Moore's Law, innovations like AutoEDA may become essential for maintaining productivity in the electronics industry.

🏷️ Themes

Artificial Intelligence, Electronic Design Automation, Natural Language Processing, Microservices Architecture

📚 Related People & Topics

Electronic design automation

Software for designing electronic systems

Electronic design automation (EDA), also referred to as electronic computer-aided design (ECAD), is a category of software tools for designing electronic systems such as integrated circuits and printed circuit boards. The tools work together in a design flow that chip designers use to design and ana...

View Profile → Wikipedia ↗

Microservices

Collection of loosely coupled services used to build computer applications

In software engineering, a microservice architecture is an architectural pattern that organizes an application into a collection of loosely coupled, fine-grained services that communicate through lightweight protocols. This pattern is characterized by the ability to develop and deploy services indep...

View Profile → Wikipedia ↗

Entity Intersection Graph

Connections for Electronic design automation:

🏢 Cadence Design Systems 2 shared
🏢 Synopsys 1 shared
🌐 Semiconductor industry 1 shared
🌐 Rosenblatt 1 shared
View full profile
Original Source
--> Computer Science > Artificial Intelligence arXiv:2508.01012 [Submitted on 1 Aug 2025 ( v1 ), last revised 24 Feb 2026 (this version, v2)] Title: AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents Authors: Yiyi Lu , Hoi Ian Au , Junyao Zhang , Jingyu Pan , Guanglei Zhou , Yiting Wang , Jingwei Sun , Ang Li , Jianyi Zhang , Hai Li , Yiran Chen View a PDF of the paper titled AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents, by Yiyi Lu and 10 other authors View PDF HTML Abstract: Electronic Design Automation remains heavily reliant on tool command language 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 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 to enable end-to-end natural language control of RTL-to-GDSII design flows. AutoEDA introduces MCP-based servers for task decomposition, tool selection, and automated error handling, ensuring robust interaction between LLM agents and EDA tools. To enhance reliability and confidentiality, we integrate locally fine-tuned LLM agents. We further contribute a benchmark generation pipeline for diverse EDA scenarios and extend CodeBLEU with Tcl-specific enhancements for domain-aware evaluation. Together, these contributions establish a comprehensive framework for LLM-driven EDA automation, bridging natural language interfaces with modern chip design flows. Empirical results show that AutoEDA achieves up to 9.9 times higher accuracy than naive approaches while reducing token usage by approximately 97% compared to in-context learning. Subjects: Artif...
Read full article at source

Source

arxiv.org

More from USA

News from Other Countries

🇬🇧 United Kingdom

🇺🇦 Ukraine