CircuitWeave：用于可执行多模态RTL生成的拓扑-行为对齐
CircuitWeave: Topology-Behavior Alignment for Executable Multimodal RTL Generation
浏览论文内容
中文总结 AI 辅助
研究如何从自然语言规范生成RTL，提出CircuitWeave合同介导多模态框架，从原理图和文本提取合同并融合，通过联合目标监督相关过程，在生成可执行RTL上取得较好效果，部分指标高于无原理图的情况。
中文摘要 AI 辅助
仅文本的语言模型从自然语言规范生成RTL，但散文可能会使连接性、寄存器边界和状态输出关系隐含，即使指定了接口和周期级行为。原理图可使这些结构关系明确，补充文本传达的行为约束。然而，简单添加图像会带来融合挑战。CircuitWeave是一个合同介导的多模态框架，从原理图中提取拓扑合同，从文本中提取行为合同，将这些记录融合成一个电路合同，序列化对应关系、缺失证据和冲突，然后仅从该合同生成RTL。通过联合目标监督合同、序列化融合、合同条件RTL生成以及从参考中反向重建覆盖的合同字段。构建了5000个可执行合格包，在VerilogEval-Human和RTLLM上，CircuitWeave取得了比无原理图的相同适应检查点更高的通过率。数据集可公开获取。
英文摘要
Text-only LLMs generate RTL from natural-language specifications, but prose can leave connectivity, register boundaries, and state-output relations implicit even when interfaces and cycle-level behavior are specified. Schematics can make these structural relations explicit and thereby complement the behavioral constraints conveyed by text. Yet simply adding an image creates a fusion challenge: direct multimodal decoding does not explicitly separate the evidence roles of text and schematics or make missing and conflicting constraints explicit before code generation.We present CircuitWeave, a contract-mediated multimodal framework that extracts a topology contract from the schematic and a behavior contract from the text. It fuses these records into a circuit contract that serializes correspondences, missing evidence, and conflicts, then generates RTL only from this contract. A joint objective supervises both contracts, serialized fusion, contract-conditioned RTL generation, and reverse reconstruction of covered contract fields from reference RTL.We construct 5,000 executable-qualified packages, each containing a specification, generated schematic, structured contracts, reference RTL, and self-checking testbench, and use the training split to adapt Qwen with LoRA. On VerilogEval-Human, CircuitWeave reaches 46.60% pass@1, 61.49% pass@5, and 65.39% pass@10. These point estimates are 8.46, 5.85, and 2.57 percentage points above those of the same adapted checkpoint without the schematic. On RTLLM, it reaches 40.00%, 48.00%, and 52.00%, two percentage points above the adapted text-only condition at each cutoff.The dataset is publicly available at https://huggingface.co/datasets/fengjiahao0421/CircuitWeave.
