---
title: "Surveys & Articles"
description: "AI for Chip surveys, engineering case studies, and technical articles."
---

- [Exploring the Agentic Frontier of Verilog Code Generation](https://arxiv.org/abs/2603.19347) (2026) — Compares prompt structures, tools, and agent wrappers under controlled conditions on CVDP, analyzing failure modes such as tool-output interpretation and crashes.
- [Human-Centered Agentic AI Workflows for RTL Verification](https://resources.sw.siemens.com/en-GB/white-paper-human-centered-agentic-ai-workflows-for-rtl-verification/) — Siemens explains the division of work among engineers, agents, and deterministic tools in RTL verification.
- [LLM for EDA in Front-End Design](https://arxiv.org/abs/2607.09616) (2026) — Discusses LLM capabilities and limitations in specification understanding, HDL, testbenches, and high-level synthesis.
- [LLMs for EDA: A Survey](https://arxiv.org/abs/2501.09655) (2025) — Surveys EDA tasks, model adaptation, and evaluation methods for LLMs.
- [Loop Engineering for Chip Design](https://agentrys.ai/case-studies/loop-engineering-for-chip-design) (2026) — Agentrys' XiangShan optimization case study connects workloads, microarchitecture parameters, correctness checks, and physical design feedback.
- [Microsoft Discovery — Learning Chip Design](https://techcommunity.microsoft.com/blog/microsoft-discovery-blog/from-ad-astra-to-semper-disco-learning-chip-design-with-microsoft-discovery/4554904) (2026) — Describes using Discovery to progress from specifications and RTL to OpenROAD physical layout, with experiments in timing and power optimization.
- [Report for NSF Workshop on AI for EDA](https://arxiv.org/abs/2601.14541) (2026) — Covers physical design, synthesis, verification, and AI tools, and discusses data and computing infrastructure.
- [The Dawn of Agentic EDA](https://arxiv.org/abs/2512.23189) (2025–2026) — Surveys agent workflows and cross-stage feedback from RTL and verification through physical design.
- [Thermonat Thermal Modeling](https://research.ibm.com/blog/from-atoms-to-chips-thermonat-models-heat-with-unprecedented-accuracy) (2026) — IBM and Ansys/Synopsys combine atomistic thermal data, reduced-order models, and a Fourier neural operator in a DARPA project to connect transistor thermal behavior with chip design.