ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 1337-1345
DOI: 10.1609/aaai.v40i2.37107 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Changwen Xing und 11 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
While Large Language Models (LLMs) demonstrate immense potential for automating integrated circuit (IC) development, their practical deployment is fundamentally limited by restricted context windows. Existing context-extension methods struggle to achieve effective semantic modeling and thorough multi-hop reasoning over extensive, intricate circuit specifications. To address this, we introduce ChipMind, a novel knowledge graph-augmented reasoning framework specifically designed for lengthy IC specifications. ChipMind first transforms circuit specifications into a domain-specific knowledge graph (ChipKG) through the Circuit Semantic-Aware Knowledge Graph Construction methodology. It then leverages the ChipKG-Augmented Reasoning mechanism, combining information-theoretic adaptive retrieval to dynamically trace logical dependencies with intent-aware semantic filtering to prune irrelevant noise, effectively balancing retrieval completeness and precision. Evaluated on an industrial-scale specification reasoning benchmark, ChipMind significantly outperforms state-of-the-art baselines, achieving an average improvement of 34.59% (up to 72.73%). Our framework bridges a critical gap between academic research and practical industrial deployment of LLM-aided Hardware Design (LAD).
Zitieren
APA
Xing, C., Wong, S., Wan, X., Lu, Y., Zhang, M., Ma, Z., Qi, L., Li, Z., Guan, N., Jiang, Z., Wang, X., & Yang, J. (2026). ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 1337-1345. https://doi.org/10.1609/aaai.v40i2.37107
Vancouver
Xing C, Wong S, Wan X, Lu Y, Zhang M, Ma Z, et al. ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):1337-1345. doi:10.1609/aaai.v40i2.37107
BibTeX
@article{Xing2026,
author = {Xing, Changwen and Wong, SamZaak and Wan, Xinlai and Lu, Yanfeng and Zhang, Mengli and Ma, Zebin and Qi, Lei and Li, Zhengxiong and Guan, Nan and Jiang, Zhe and Wang, Xi and Yang, Jun},
title = {ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {2},
pages = {1337--1345},
doi = {10.1609/aaai.v40i2.37107}
}
EUVIMED