Live intelligence

Latest AI updates

3 updates
Research

AnalogLayoutWorld: A New Benchmark for Agentic Analog Layout Design

AnalogLayoutWorld is an open-source benchmark with 40 expert-reviewed tasks for end-to-end analog circuit layout generation from fixed transistor-level netlists. It integrates a design environment with physical and post-layout electrical verification and objective layout quality metrics. Across 13 model-harness configurations, 91.1% of attempts produce GDS layouts but only 23.0% meet acceptance criteria, with the internally developed Novara agent achieving the highest aggregate score. The analysis suggests reasoning efficiency and effective use of verification feedback are key to sustaining quality as task complexity grows.

AI agentselectronic design automationbenchmarking
Research

Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

This arXiv paper examines autonomous LLM-agent approaches for RTL and synthesis optimization across realistic benchmarking, tool-grounded RTL rewriting, and synthesis-script tuning. It presents Dr. RTL, a multi-agent framework that automates critical-path analysis, RTL rewriting, and implementation-level evaluation while accumulating reusable optimization skills. On 20 real-world RTL designs, the authors report average WNS/TNS improvements of 21%/17% and a 6% area reduction over commercial synthesis. The paper also outlines a vision for AI-native design automation spanning architectural, RTL, and EDA algorithm spaces.

RTL optimizationElectronic design automationLLM agents
Research

AMSchem turns AMS netlists into readable schematics with a verifier-guided LLM agent

Researchers present AMSchem, a training-free agentic framework that automatically converts analog and mixed-signal netlists into human-readable schematics. The system splits circuit-aware visual planning (DrawingIntent) from executable schematic geometry (SchematicIR) and applies localized visual feedback with bounded, revalidated repair patches, while deterministic validators enforce device preservation, pin-net consistency and geometric correctness. On the 40-circuit schematic subset of the new AMSchem-Bench (64 circuits, 12 types), AMSchem with gpt-5.5 reaches 85.0% validity versus 32.5% for direct generation. Used as a visual feedback module in LLM-based analog design, it resolves all 13 previously failed cases from the AnalogCoder benchmark across five models.

analog and mixed-signal design automationLLM agentselectronic design automation