ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xing, Changwen, Wong, SamZaak, Wan, Xinlai, Lu, Yanfeng, Zhang, Mengli, Ma, Zebin, Qi, Lei, Li, Zhengxiong, Guan, Nan, Jiang, Zhe, Wang, Xi, Yang, Jun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911303956692992
author Xing, Changwen
Wong, SamZaak
Wan, Xinlai
Lu, Yanfeng
Zhang, Mengli
Ma, Zebin
Qi, Lei
Li, Zhengxiong
Guan, Nan
Jiang, Zhe
Wang, Xi
Yang, Jun
author_facet Xing, Changwen
Wong, SamZaak
Wan, Xinlai
Lu, Yanfeng
Zhang, Mengli
Ma, Zebin
Qi, Lei
Li, Zhengxiong
Guan, Nan
Jiang, Zhe
Wang, Xi
Yang, Jun
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2512_05371
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications
Xing, Changwen
Wong, SamZaak
Wan, Xinlai
Lu, Yanfeng
Zhang, Mengli
Ma, Zebin
Qi, Lei
Li, Zhengxiong
Guan, Nan
Jiang, Zhe
Wang, Xi
Yang, Jun
Artificial Intelligence
Hardware Architecture
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).
title ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications
topic Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2512.05371