Papers for

electronic design automation developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

OpenLayout platform uses AI agents to improve chip design accuracy

OpenLayout: An Open and Agentic-Driven Platform for Holistic VLSI Physical Design and Benchmarking

Abstract: Physical design automation of very large-scale integrated circuits (VLSI) has made significant strides, progressing from single-stage placement and routing toward increasingly integrated full-flow implementation. Yet, existing approaches struggle with the vast design space optimization (DSO) arising from diverse technology nodes, circuit designs, and varied constraints. The substantial runtime of physical-design tools further exacerbates this challenge, leaving industrial workflows heavily dependent on experienced engineers to navigate the design space and achieve power, performance, and area (PPA) targets, incurring significant engineering effort. We argue that large language models (LLMs) with strong reasoning capabilities, enriched with distilled human design expertise, offer a promising path toward efficient and automated DSO. Unlike traditional algorithms, LLMs can interpret complex design contexts and naturally incorporate human expertise expressed in natural language for reasoning, acting, observing, and adapting throughout the design process, a capability that conventional optimization methods cannot exploit. To this end, we present OpenLayout, an agentic platform that leverages multi-agent collaboration with embedded design knowledge to enable self-iterative DSO. We further introduce OpenLayout-Bench, a benchmark targeting advanced technology nodes with commercial EDA tools to systematically evaluate physical design automation capabilities of LLMs. Experimental results demonstrate that OpenLayout achieves state-of-the-art performance, with approximately 20% accuracy improvement over baseline methods. Our work is open-sourced at https://github.com/fenggev56/OpenLayout

Fri 13 NovHardware Architecture
The gist
Designing computer chips is very complicated and takes a lot of time and expert knowledge. The authors show that using large language models—advanced AI that understands and reasons like humans—can help automate this process. Their platform, OpenLayout, uses multiple AI agents working together to improve chip design, making it about 20% more accurate than older methods. They also created a benchmark to test this approach on new technology. This work is openly shared for others to use and build upon.
Open → 2611.18517v1

AnalogLayoutWorld benchmark tests AI for analog circuit design tasks

AnalogLayoutWorld: An Open Benchmark for Agentic Analog Layout Design

Abstract: Coding agents have demonstrated strong capabilities in software development, yet their ability to tackle long-horizon engineering tasks governed by physical constraints remains less understood. We study this question through analog circuit layout, which demands domain knowledge, geometric reasoning, and iterative interaction with design and verification tools. We introduce \textbf{AnalogLayoutWorld}, an open-source agent benchmark with 40 expert-reviewed tasks for end-to-end layout generation from fixed transistor-level netlists. It combines an integrated design environment with independent physical and post-layout electrical verification, as well as objective layout quality metrics co-designed with analog layout experts. Across 13 model--harness configurations, 91.1\% of attempts produce GDS layouts, but only 23.0\% satisfy the benchmark's acceptance criteria. We also evaluate Novara, an internally developed agent system, which achieves the highest reported aggregate score. Our analysis links performance differences to test-time scaling under fixed budgets, suggesting that reasoning efficiency and effective use of verification feedback help sustain design quality as task complexity grows.

Thu 12 NovArtificial Intelligence
The gist
Designing analog circuits is hard because it needs specialized knowledge and careful planning. The authors created AnalogLayoutWorld, a set of 40 challenging tasks that test if AI agents can generate layouts of analog circuits. They also provide tools to check if the designs work well physically and electrically. Their experiments show many AI attempts create layouts, but only a few meet strict quality standards. They suggest better reasoning and using feedback effectively help AI handle more complex designs.
Open → 2611.16991v1