EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

VTR-LLM: Multi-Agent LLM Framework for Automated Debugging of FPGA CAD Flows

Mohamed A. Elgammal, Jamie Wu, Lynne Liu, Taehoon Kim, Vaughn Betz

ACM Transactions on Reconfigurable Technology and Systems · 31.12.2026 · 19 (4) · 1-26

DOI: 10.1145/3829373 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Reconfigurable Technology and Systems, online erschienen am 21.10.2026. Verfasst von Mohamed A. Elgammal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 88 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern FPGA computer-aided design (CAD) flows have grown increasingly complex, integrating numerous stages, configuration parameters, timing constraints, and physical implementation specifications. As designs scale, failures often arise from subtle interactions across command-line options and constraint files, making debugging time-consuming and heavily dependent on expert knowledge. Identifying the root cause of such failures and determining the appropriate corrective action remains a major productivity bottleneck in CAD workflows. This article presents VTR-LLM , a fully automated, multi-agent framework for diagnosing and resolving failures in the Verilog-to-Routing (VTR) CAD flow. VTR-LLM leverages large language models (LLMs) in combination with retrieval-augmented generation (RAG) and specialized agents that target distinct sources of errors, including command-line invocations, timing constraints (i.e., Synopsys Design Constraints or SDC), and floorplanning specifications. A Classification Agent dynamically assigns each failure to the most appropriate agent and supports sequential resolution for compound failures involving multiple error sources. The system leverages LLMs without requiring fine-tuning, enabling the use of the latest models such as GPT-OSS-120B, by using RAG and intelligent agents to add domain-specific context and behaviors. We evaluate VTR-LLM using a dataset of 92 distinct VTR failure cases spanning multiple error patterns and levels of complexity. VTR-LLM can resolve 95% of all failures fully automatically, with robust performance across error categories. Additional studies demonstrate the impact of documentation retrieval scope, tool iteration, and LLM model choice on resolution accuracy and inference cost.

Förderung

  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Elgammal, M. A., Wu, J., Liu, L., Kim, T., & Betz, V. (2026). VTR-LLM: Multi-Agent LLM Framework for Automated Debugging of FPGA CAD Flows. ACM Transactions on Reconfigurable Technology and Systems, 19(4), 1-26. https://doi.org/10.1145/3829373

Vancouver

Elgammal MA, Wu J, Liu L, Kim T, Betz V. VTR-LLM: Multi-Agent LLM Framework for Automated Debugging of FPGA CAD Flows. ACM Transactions on Reconfigurable Technology and Systems. 2026;19(4):1-26. doi:10.1145/3829373

BibTeX
@article{Elgammal2026,
  author = {Elgammal, Mohamed A. and Wu, Jamie and Liu, Lynne and Kim, Taehoon and Betz, Vaughn},
  title = {VTR-LLM: Multi-Agent LLM Framework for Automated Debugging of FPGA CAD Flows},
  journal = {ACM Transactions on Reconfigurable Technology and Systems},
  year = {2026},
  volume = {19},
  number = {4},
  pages = {1--26},
  doi = {10.1145/3829373}
}
Kostenlos starten →