arXiv：cs.AI· Awani Khodkumbhe, Yunfei Feng, Raj Rangarajan, Kevin Wang, Kamal Sahota·· 3 小时前
RFChipAgent：面向模拟/RF 芯片设计的多智能体 AI 流程
RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
AI 导读
RFChipAgent 是首个用于模拟/RF 电路端到端设计自动化的 LLM 多智能体流程，由 AI 智能体在人工监督下协同编排完整设计流程。它包含多模态 RAG 子系统与私有的逐文档 FAISS 索引、拓扑智能体及原理图/测试台智能体、结合 TPE 与 CMA-ES 的闭环混合电路尺寸优化引擎，以及带信任评分的仿真数据库。
正文
Abstract:Analog/RF circuits remain the critical interface between digital computation and the physical world, and emerging standards from Wi-Fi 7 to 6G place stringent demands on them, yet analog/RF design remains one of the most labor-intensive steps in chip development. We present RFChipAgent, a first-of-its-kind multi-agent flow of large language model (LLM) agents for end-to-end analog/RF circuit design automation, in which AI agents collaboratively orchestrate the complete design flow under human supervision. RFChipAgent is built around four technical pillars. First, a multimodal retrieval-augmented generation (RAG) subsystem with private per-document FAISS indexing extracts design knowledge from existing engineering documentation. Second, a topology agent drives topology selection, and a schematic and testbench agent automates circuit and testbench assembly. Third, a closed-loop hybrid circuit-sizing engine combines Tree-structured Parzen Estimator (TPE) and CMA-ES optimization, evaluating every candidate in a simulator-in-the-loop framework. Fourth, a trust-scored simulation database accumulates verified performance data and builds an adaptive optimization model that informs subsequent trials. We validate RFChipAgent on a family of GF22FDSOI 60 GHz wideband mm-wave low-noise amplifier (LNA) topologies, demonstrating automated topology generation, specification-driven design-space exploration, and simulator-guided optimization. Experimental results show substantial reductions in design effort while maintaining signoff-quality verification. This work establishes a foundation for LLM-driven multi-agent electronic design automation (EDA) for analog/RF circuits.
| Comments: | 6 pages, 4 figures. Submitted to ACM/IEEE for possible publication |
| Subjects: | Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Systems and Control (eess.SY) |
| ACM classes: | B.7.2; I.2.11 |
| Cite as: | arXiv:2610.10858 [cs.AR] |
| (or arXiv:2610.10858v1 [cs.AR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10858 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Awani Khodkumbhe [view email]
[v1]
Wed, 7 Oct 2026 20:02:33 UTC (636 KB)
来源：arXiv：cs.AI · arxiv.org