← 研踪 PaperTrailarXiv:2611.19056 · v2
Run, Read Back, Refine: Observation Fidelity in Execution-Grounded EDA Agents
首次提交 2026-11-14 08:58
版本更新 2026-11-18 18:58
雷达观测 2026-11-19 15:04
摘要
Design engineers lose the most time orchestrating flows and patching the gaps where closed EDA tools refuse to interoperate. We present an execution-grounded LLM agent for PyAether, SKILL, and Tcl that closes a generate-execute-refine loop over unified MCP tools (API retrieval, documentation, sandbox execution) and is already deployed in production EDA flows, with a grounding-gap framework positing that EDA-scripting correctness is bottlenecked by observation fidelity at the L4 (situated) layer, which model scale alone cannot reach. On EDA-Scripting-Bench (449 tasks, three languages, four commercial runtimes), the system reaches 76.5% pooled Pass@1 versus 19.7% (pure LLM): the system-level observation axis spans 56.8 percentage points with the model fixed, exceeding the 23.3-percentage-point backbone range with the harness fixed---two axes answering different questions; observation is an under-invested axis whose returns are measurable and graded.
作者备注:7 pages, 1 figure, 4 tables. Manuscript prepared for the DAC 2027 Research Track (IEEE conference format)
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-18 18:58 · 最新观测版本
Run, Read Back, Refine: Observation Fidelity in Execution-Grounded EDA Agents
Design engineers lose the most time orchestrating flows and patching the gaps where closed EDA tools refuse to interoperate. We present an execution-grounded LLM agent for PyAether, SKILL, and Tcl that closes a generate-execute-refine loop over unified MCP tools (API retrieval, documentation, sandbox execution) and is already deployed in production EDA flows, with a grounding-gap framework positing that EDA-scripting correctness is bottlenecked by observation fidelity at the L4 (situated) layer, which model scale alone cannot reach. On EDA-Scripting-Bench (449 tasks, three languages, four commercial runtimes), the system reaches 76.5% pooled Pass@1 versus 19.7% (pure LLM): the system-level observation axis spans 56.8 percentage points with the model fixed, exceeding the 23.3-percentage-point backbone range with the harness fixed---two axes answering different questions; observation is an under-invested axis whose returns are measurable and graded.
查看此版本解读 →查看此版本原文 ↗