Delta-Seeker: Closed-Loop Generative Search for Novel Circuit Design Discovery

📄 arXiv: 2610.41227v1 📥 PDF

作者: Dinithi Jayasuriya, Devangshu Dutta, Aravind Saravanan, Nilesh Ahuja, Amanda Rios, Amit Trivedi

分类: eess.SY

发布日期: 2026-10-30


💡 一句话要点

提出Delta-Seeker以解决电路设计发现问题

🎯 匹配领域: 支柱八:物理动画 (Physics-based Animation)

关键词: 电路设计 生成模型 闭环搜索 拓扑发现 电气性能 结构有效性 优化设计

📋 核心要点

  1. 现有电路设计方法在探索新拓扑时面临结构有效性和电气行为可重复性的问题。
  2. Delta-Seeker通过闭环搜索框架,结合多种技术手段,支持电路设计的发现,确保生成结构的有效性。
  3. 实验结果显示,Delta-Seeker在生成有效设计数量和降低故障候选比例方面均有显著提升。

📝 摘要(中文)

生成模型在电路合成和优化中越来越多地被使用,然而其在设计发现中的应用尚未得到充分探索。本文提出Delta-Seeker,一个闭环电路搜索框架,结合了拓扑生成、结构检查、SPICE仿真、Pareto选择和反馈机制。通过交叉代际反馈,Delta-Seeker显著提高了结构有效子代的数量,并降低了故障候选的比例。在运算放大器拓扑发现中,Delta-Seeker生成了54个在多次独立重缩放中仍然可行的设计,显示出其在电路操作变化中的独立验证能力。实验结果表明,闭环生成搜索能够支持超越结构新颖性的电路发现。

🔬 方法详解

问题定义:本文旨在解决生成模型在电路设计发现中的应用不足,特别是在确保生成结构的有效性和电气行为可重复性方面的挑战。现有方法往往无法有效探索新拓扑,导致设计的局限性。

核心思路:Delta-Seeker的核心思路是通过闭环反馈机制,结合拓扑生成、结构检查和电气性能验证,来支持电路设计的发现。该方法通过不断调整生成策略,确保生成的电路设计不仅新颖且可行。

技术框架:Delta-Seeker的整体架构包括多个模块:首先是离散扩散用于拓扑生成和变异;其次是结构检查和SPICE仿真用于电气性能评估;然后是Pareto选择用于优化设计;最后是反馈机制用于指导后续的拓扑生成。

关键创新:Delta-Seeker的主要创新在于其闭环生成搜索策略,通过交叉代际反馈显著提高了结构有效子代的数量,并降低了故障候选比例。这一方法与传统的固定控制方法相比,能够更有效地发现新拓扑。

关键设计:在设计中,Delta-Seeker采用了独立重缩放分析,并在搜索后进行操作角分析。此外,去除交叉代际记忆会显著影响独立鲁棒发现的数量,显示出反馈机制的重要性。实验中还使用了多种性能指标来评估设计的有效性和鲁棒性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,Delta-Seeker在运算放大器拓扑发现中生成了54个在至少三次独立重缩放中可行的设计,相较于固定控制方法的38个设计有显著提升。此外,故障候选比例从0.925降低至0.761,显示出该方法在电路设计发现中的有效性。

🎯 应用场景

Delta-Seeker的研究成果在电路设计领域具有广泛的应用潜力,尤其是在新型电路拓扑的发现和优化方面。其方法可以应用于集成电路设计、电子设备开发等领域,推动电路设计的创新与效率提升。未来,该框架有望与其他生成模型结合,进一步拓展其应用范围。

📄 摘要(原文)

Generative models are increasingly used for circuit synthesis and optimization by proposing topologies, sizing devices, and exploring large design spaces. We investigate whether they can instead support design discovery, where generated structures must depart from known designs while producing reproducible electrical behavior. We propose Delta-Seeker, a closed-loop circuit search framework that combines discrete diffusion for topology generation and mutation with structural checking, SPICE-in-the-loop sizing, Pareto selection, and feedback from prior search outcomes. The search controller uses progress and recurring structural failures to allocate evaluation effort and steer subsequent topology generation, while independent re-sizing and operating-corner analysis are performed only after search. In generator-only experiments, cross-generation feedback increases structurally valid children from 143 to 945 and reduces the faulty-candidate fraction from 0.925 to 0.761. In op-amp topology discovery at matched sizing cost, Delta-Seeker yields 54 designs that remain feasible in at least three of four independent re-sizings and 18 that additionally pass device-level checks and supply-temperature corner analysis, compared with 38 and 10 under fixed control. Removing cross-generation memory reduces independently robust discoveries from 54 to 43 and seven-corner robust discoveries from 40 to 27. In DC-DC converter search, nearest-parent analysis identifies a corpus-absent topology whose generated switching current path changes its nearest training-corpus parent from infeasible at all four operating corners to feasible at all four, while increasing median efficiency from 31.2% to 98.96%. These results show that closed-loop generative search can support circuit discovery beyond structural novelty by identifying new topologies with independently verified changes in circuit operation.