SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and Summarization
Not on the map. Why?
Abstract (arXiv)
Register-Transfer Level (RTL) synthesis and summarization are central to hardware design automation but remain challenging for Large Language Models (LLMs) due to rigid HDL syntax, limited supervision, and weak alignment with natural language. Existing prompting and retrieval-augmented generation (RAG) methods have not incorporated symbolic planning, limiting their structural precision. We introduce SYMDIREC, a neuro-symbolic framework that decomposes RTL tasks into symbolic subgoals, retrieves relevant code via a fine-tuned retriever, and assembles verified outputs through LLM reasoning. Supporting both Verilog and VHDL without LLM fine-tuning, SYMDIREC achieves ~20% higher Pass@1 rates for synthesis and 15-20% ROUGE-L improvements for summarization over prompting and RAG baselines, demonstrating the benefits of symbolic guidance in RTL tasks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 17 Mar 2026.
Builds on
20 of 29 references.
References · 20
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
- 2023Code Llama: Open Foundation Models for Codecited by 2,139
- 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
- 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
- 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
- 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
- 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
- 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 252
8 more
- 2021Retrieval Augmented Code Generation and Summarizationcited by 149
- 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 127
- 2024Granite Code Models: A Family of Open Foundation Models for Code Intelligencecited by 117
- 2024VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Toolcited by 85
- 2024GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuningcited by 40
- 2025HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDLcited by 17
- 2024VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generationcited by 15
- 2025Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generationcited by 10
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
- 2026ChipCraftBrain: Validation-First RTL Generation via Multi-Agent Orchestration
- 2026CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs
- 2026RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models
- 2026LLM4RTL: Tool-Assisted LLM for RTL Generation
- 2025RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation
- 2025DeepV: A Model-Agnostic Retrieval-Augmented Framework for Verilog Code Generation with a High-Quality Knowledge Base
- 2025TuRTLe: A Unified Evaluation of LLMs for RTL Generation