一种多智能体协同模拟电路分析推理方法、系统及设备
By employing a multi-agent collaborative analog circuit analysis and reasoning method, the problem of poor accuracy and consistency of large language models in analog circuit analysis and reasoning is solved, enabling high-precision automated processing of complex tasks and reducing circuit design complexity.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN UNIV
- Filing Date
- 2026-03-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing large language models lack reasoning capabilities in analog circuit analysis and reasoning, making it difficult to decompose complex tasks into ordered steps, resulting in low accuracy and poor consistency of reasoning results, which cannot meet the needs of engineering applications.
A multi-agent collaborative analog circuit analysis and reasoning method is adopted. By selecting agents to retrieve knowledge entries from the domain knowledge base and sub-circuit library, the pre-analysis agents decompose the task into a sequence of sub-tasks, and the analysis agents perform reasoning analysis to generate physical quantity expression results in LaTeX format.
It achieves full-process automation and high-precision reasoning from task reception to result output, reduces the complexity of circuit analysis and design costs, and provides efficient and reliable technical support for fields such as wireless communication and autonomous driving perception.
Smart Images
Figure CN121902730B_ABST