A Large Language Model-based Multi-Agent Framework for Analog Circuits' Sizing Relationships Extraction

2025-06-23

AI Summary

To address the challenges of excessively large search spaces and difficulty in automatically incorporating domain knowledge during pre-layout device sizing optimization for analog circuits, this paper proposes the first large language model (LLM)-based multi-agent framework. It autonomously mines implicit sizing constraints from vast academic literature, enabling effective search-space pruning. By integrating multi-agent collaboration with natural language processing, the framework converts unstructured design knowledge into executable sizing constraints, significantly improving optimization efficiency. Experimental evaluation on three representative analog circuits demonstrates speedups of 2.32×–26.6× and substantial reduction in search-space volume. This work pioneers the deep integration of LLM-driven knowledge discovery into the analog circuit automated design flow, advancing the substantive convergence of AI techniques with traditional EDA methodologies.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

In the design process of the analog circuit pre-layout phase, device sizing is an important step in determining whether an analog circuit can meet the required performance metrics. Many existing techniques extract the circuit sizing task as a mathematical optimization problem to solve and continuously improve the optimization efficiency from a mathematical perspective. But they ignore the automatic introduction of prior knowledge, fail to achieve effective pruning of the search space, which thereby leads to a considerable compression margin remaining in the search space. To alleviate this problem, we propose a large language model (LLM)-based multi-agent framework for analog circuits' sizing relationships extraction from academic papers. The search space in the sizing process can be effectively pruned based on the sizing relationship extracted by this framework. Eventually, we conducted tests on 3 types of circuits, and the optimization efficiency was improved by $2.32 sim 26.6 imes$. This work demonstrates that the LLM can effectively prune the search space for analog circuit sizing, providing a new solution for the combination of LLMs and conventional analog circuit design automation methods.

Problem

• Extracting analog circuit sizing relationships from papers
• Pruning search space using LLM-based multi-agent framework
• Improving optimization efficiency in analog circuit design

Innovation

• LLM-based multi-agent framework for circuit sizing
• Automatic prior knowledge introduction for pruning
• Improved optimization efficiency by 2.32-26.6 times