用大模型自动优化芯片设计参数，比传统方法更省资源、效果更好。
ORFS-agent: Tool-Using Agents for Chip Design Optimization
- 基于大模型的迭代代理，自适应探索参数配置
- 在六个基准上减少40%迭代次数，性能提升最高2.7%
- 支持自然语言指令，可私有部署且无需微调
机器学习广泛应用于复杂工程流程优化。在集成电路设计中，现代流程（如寄存器传输级到物理布局）涉及数千个参数配置，微小变动可能显著影响性能、功耗和面积。近年来大语言模型（LLM）为高维优化任务中的学习与推理提供了新机遇。本文提出ORFS-agent，一种基于LLM的迭代优化代理，用于开源硬件设计流程中的参数自动调优。该代理自适应探索参数配置，在资源效率和最终设计指标上优于标准贝叶斯优化方法。在ASAP7和SKY130HD六个基准测试中，采用思维模型后端（Sonnet 4.6 [69] 和 Kimi K2.5 [28]）使几何均值归一化布线长度、有效时钟周期及协同优化目标分别提升最多1.0%、1.3%和2.7%，且迭代次数减少40%；开源版Kimi K2.5与Sonnet 4.6差距不超过0.24%，支持私有部署。相较早期Sonnet 3.5后端，性能提升最高达7.5%、3.1%和4.0%。可选检索工具加速早期收敛但不影响最终结果。通过遵循自然语言目标权衡不同指标，ORFS-agent展现出灵活可解释的多目标与约束优化能力。关键在于其模块化与模型无关性，可无缝接入任意前沿大模型，无需额外微调。我们还报告了对齐检查点的轨迹与推理摘要，记录代理决策过程。
原文摘要 · Abstract (English)
Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In integrated circuit design, modern flows (e.g., register-transfer level to physical layout) involve extensive configuration via thousands of parameters, and small changes can have large downstream impacts on design performance, power, and area. Recent advances in Large Language Models (LLMs) offer new opportunities for learning and reasoning within such high-dimensional optimization tasks. In this work, we introduce ORFS-agent, an LLM-based iterative optimization agent that automates parameter tuning in an open-source hardware design flow. ORFS-agent adaptively explores parameter configurations, demonstrating improvements over standard Bayesian optimization approaches in terms of resource efficiency and final design metrics. Across six benchmarks on ASAP7 and SKY130HD, thinking-model backends (Sonnet 4.6 [69] and Kimi K2.5 [28]) improve the geometric-mean normalized wirelength, effective clock period, and co-optimization objectives by up to 1.0%, 1.3%, and 2.7% over OR-AutoTuner while using 40% fewer iterations; the open-weight Kimi K2.5 remains within 0.24% of Sonnet 4.6, enabling private deployment. Relative to the earlier Sonnet 3.5 backend, these thinking models improve the same objectives by up to 7.5%, 3.1%, and 4.0%. Optional retrieval tools accelerate early convergence but do not improve final endpoints. By following natural language objectives to trade off certain metrics for others, ORFS-agent demonstrates a flexible and interpretable framework for multi-objective and constrained optimization. Crucially, ORFS-agent is modular and model-agnostic, and can be plugged into any frontier LLM without any further fine-tuning. We also report checkpoint-aligned trajectories and reasoning summaries that document the agent's decision process.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。