Research map / Large language models / Retrieval and knowledge
ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications
Changwen Xing, SamZaak Wong, Xinlai Wan, Yanfeng Lu, Mengli Zhang, Zebin Ma, Lei Qi, Zhengxiong Li, Nan Guan, Zhe Jiang, Xi Wang, Jun Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use multi-turn iterative ChipKG reasoning instead of single pass (ablation) | ChipMind · SpecEval-QA | Atomic-ROUGE F1: 0.83 -> 0.95 | Improved |
| use ChipKG triple schema instead of generic OpenIE (ablation) | ChipMind · SpecEval-QA | Atomic-ROUGE F1 | Improved |
| use ChipKG instead of plain vector RAG (ablation) | ChipMind · SpecEval-QA | Atomic-ROUGE F1 | Improved |
| use adaptive-K retrieval instead of fixed K (ablation) | ChipMind · SpecEval-QA cross-module config localization | Atomic-ROUGE F1 | Improved |
| add CSA-guided semantic filtering as K increases (ablation) | ChipMind · SpecEval-QA | Atomic-ROUGE F1 | Improved |
| ChipKG single-pass vs HippoRAG 2 as KG-RAG (ablation) | ChipMind · SpecEval-QA | Atomic-ROUGE F1: 0.76 -> 0.83 | Improved |
| ChipMind vs best baseline per category | ChipMind · SpecEval-QA | Atomic-ROUGE F1: GPT-4.1 0.79 -> 0.95; HippoRAG 2 0.76 -> 0.95; IRCoT 0.81 -> 0.95 | Improved |
| iterative sub-queries for retrieval vs single-pass retrieval | ChipMind · SpecEval-QA | System Recall@20: 70.5% / 86.8% -> 99.2% | Improved |
| Atomic-ROUGE vs BERTScore agreement with human ratings | Atomic-ROUGE · Atomic-ROUGE validation | Pearson correlation: 0.71 -> 0.83 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HippoRAG 2 — HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (NeurIPS 2024) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design (ICLR 2025 · similarity 0.87)
- CircuitSense: A Hierarchical Circuit System Benchmark Bridging Visual Comprehension and Symbolic Reasoning in Engineering Design Process (ICLR 2026 · similarity 0.86)
- Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization (ICLR 2024 · similarity 0.85)
- A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design (ICML 2024 · similarity 0.84)
- PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured Verification (NeurIPS 2026 · similarity 0.83)
- BetterV: Controlled Verilog Generation with Discriminative Guidance (ICML 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
