EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit
This addresses the need for automated, interpretable schematic generation in analog circuit design, though it is incremental as it builds on existing LLM-based methods by adding multimodal capabilities.
The authors tackled the problem of generating visual circuit schematics from textual SPICE netlists, which lack visual interpretability for designers, by proposing EEschematic, an AI agent that uses a multimodal LLM to produce schematics with high visual quality and structural correctness, as demonstrated on circuits like a CMOS inverter and telescopic cascode amplifier.
Circuit schematics play a crucial role in analog integrated circuit design, serving as the primary medium for human understanding and verification of circuit functionality. While recent large language model (LLM)-based approaches have shown promise in circuit topology generation and device sizing, most rely solely on textual representations such as SPICE netlists, which lack visual interpretability for circuit designers. To address this limitation, we propose EEschematic, an AI agent for automatic analog schematic generation based on a Multimodal Large Language Model (MLLM). EEschematic integrates textual, visual, and symbolic modalities to translate SPICE netlists into schematic diagrams represented in a human-editable format. The framework uses six analog substructure examples for few-shot placement and a Visual Chain-of-Thought (VCoT) strategy to iteratively refine placement and wiring, enhancing schematic clarity and symmetry. Experimental results on representative analog circuits, including a CMOS inverter, a five-transistor operational transconductance amplifier (5T-OTA), and a telescopic cascode amplifier, demonstrate that EEschematic produces schematics with high visual quality and structural correctness.