Metraipolis › archive › dc_5605e00d8a79

LLM-based Hardware Development with Hierarchical IRs and End-to-End Multi-Agent Workflow — arXiv:2608.30659

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30659
License (as archived)
CC0-1.0
Archived
2026-10-17T07:41:00.964Z
SHA-256 of the archived text
efe03639738736873ac5b3fb5ffb897d4583b478639ceb96745328de6b40fbab
Stable URL of this page
https://metraipolis.com/documento/dc_5605e00d8a79

How to cite

LLM-based Hardware Development with Hierarchical IRs and End-to-End Multi-Agent Workflow — arXiv:2608.30659 — arXiv (en), https://arxiv.org/abs/2608.30659 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5605e00d8a79 (Metraipolis archive dc_5605e00d8a79, sha256 efe03639738736873ac5b3fb5ffb897d4583b478639ceb96745328de6b40fbab)
BibTeX
@misc{dc5605e00d8a79,
  title = {LLM-based Hardware Development with Hierarchical IRs and End-to-End Multi-Agent Workflow — arXiv:2608.30659},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30659},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5605e00d8a79; sha256 efe03639738736873ac5b3fb5ffb897d4583b478639ceb96745328de6b40fbab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30659. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used in software development, but their use in complex hardware design remains limited. This gap stems from both the scarcity of public hardware training data and the fundamentally different methodologies used in hardware design. In particular, applying LLMs to hardware requires more than direct RTL generation: the model must understand module boundaries, inter-module connections, and verification requirements. In this paper, we present an LLM-based hardware development framework with hierarchical intermediate representations (IRs) and an end-to-end multi-agent workflow. The core idea is to provide an abstraction of hardware design to LLMs through two structured IRs: Architectural Sketch, which captures module topology and interconnection, and Operational Specification, which defines per-module functionality and interfaces. Our framework uses these IRs to decompose a complex design into sub-modules, specify the per-block functionality, and derive how each module should be tested and verified. We incorporate a multi-agent debug loop in the framework, allowing agents to get the error feedback and control the debug details such as the signals to be probed for simulation. We evaluate our framework on Verilog-Eval benchmark, achieving a pass@5 rate of 95.5%, which surpasses current state-of-the-art LLM generation frameworks. To better assess performance on complex, realistic designs, we introduce a new case study spanning applications from general-purpose processors to digital signal processing systems. Experimental results indicate that such complex designs exceed the capabilities of existing approaches, whereas our framework is the only one capable of producing functional end-to-end design. Our generated RTL follows all industry-standard design rules, is lint-clean, functionally correct and fully synthesizable.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.MA).
Categorie arXiv: Hardware Architecture (cs.AR) ; Multiagent Systems (cs.MA); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.30659 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:27:42.013Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).