arXiv · 2611.19056
Run, Read Back, Refine: Observation Fidelity in Execution-Grounded EDA Agents
Abstract
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yang Liu, Shiwei Hou, Xiyuan Chen, Sen Yuan, Shao You, Feifan Chen, Wencheng Li, Shuyang Hu, Emma Xia, Xiaojing Lu, Wenchuan Zhang, Hao Wang, Fan Xu, Yanfeng Li, Hongwen Li, Yiming Zhu. 2026-11-14. Run, Read Back, Refine: Observation Fidelity in Execution-Grounded EDA Agents. https://searcharxiv.com/abs/2611.19056
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.