发表机构
Texas A&M University（得克萨斯农工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出EDATracer框架，将EDA工件组织为知识图谱搭配语义向量索引，构建含2787个开源芯片设计的18.9GB数据集及90题基准，使LLM智能体跨工件检索证据，准确率优于Cursor、Claude Code且token用量更少。
AI 中文摘要
现代芯片设计依赖电子设计自动化（EDA）工具，这些工具会生成大量异构工件，包括源文件、脚本、日志、网表和报告。分析这些工件对调试、优化和设计流程理解至关重要，但由于相关证据往往分布在多种工件类型和设计阶段，该工作仍存在难度。尽管大语言模型（LLM）智能体在EDA辅助方面展现出潜力，但现有方法缺乏用于大规模跨工件分析的公开基准，且常难以将推理建立在工具生成的证据之上。本文提出EDATracer，这是一个基于证据的EDA工件分析智能体框架。EDATracer将设计工件组织为知识图谱，并搭配语义向量索引，使LLM智能体能够跨源文件、日志、网表和报告检索证据。我们整理了一个18.9GB的数据集，包含2787个可综合的开源芯片设计，并引入了一个包含90个问题的基准，涵盖事实、统计和推理任务。在评估的智能体中，EDATracer实现了最佳的pass@1准确率，平均比Cursor和Claude Code分别高出6.4和7.2个百分点，同时使用的token量减少了2.0至3.2倍。
英文摘要
Modern chip design relies on electronic design automation (EDA) tools that generate large, heterogeneous artifacts, including source files, scripts, logs, netlists, and reports. Analyzing these artifacts is critical for debugging, optimization, and design-flow understanding, but remains difficult because relevant evidence is often distributed across many artifact types and design stages. Although LLM agents show promise for EDA assistance, existing approaches lack public benchmarks for large-scale cross-artifact analysis and often struggle to ground reasoning in tool-generated evidence. We present EDATracer, an agentic framework for evidence-grounded EDA artifact analysis. EDATracer organizes design artifacts into a knowledge graph paired with a semantic vector index, enabling LLM agents to retrieve evidence across source files, logs, netlists, and reports. We curate an 18.9 GB dataset of 2,787 synthesizable open-source chip designs and introduce a 90-question benchmark spanning factual, statistical, and reasoning tasks. Across evaluated agents, EDATracer achieves the best pass@1 accuracy, outperforming Cursor and Claude Code by 6.4 and 7.2 percentage points on average, while using 2.0-3.2x fewer tokens.
