---
title: "RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.41225v1"
permalink: "https://feed.astralor.com/items/itm_1062a0438f0057afbdeb413a"
published: "2026-10-30T04:03:39.000Z"
score: 55
channel: "tech"
tags: ["LLM","RAG","多模态","RTL-Interact","Training EDA-Interactive Models","Multi-Task RTL Design","Large","RTL"]
---

# RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design

## 速览

Large language models offer a promising route to register-transfer-level (RTL) design, but reliable implementations require checking and revision based on electronic design automation (EDA) tools' feedback. Existing RTL…

## 关键点

- Large language models offer a promising route to register-transfer-level (RTL) design, but reliable implementations require checking and revision based on electronic design automation (EDA) tools' feedback.
- Existing RTL-specialized models often lack learned interaction with such EDA tools or rely on separate generation and repair components.
- We introduce RTL-Interact, a multi-task post-training framework that trains a single RTL-specialized model to generate RTL, construct task-appropriate EDA checks, and revise implementations using tool feedback.

## 全文

Large language models offer a promising route to register-transfer-level (RTL) design, but reliable implementations require checking and revision based on electronic design automation (EDA) tools' feedback. Existing RTL-specialized models often lack learned interaction with such EDA tools or rely on separate generation and repair components. We introduce RTL-Interact, a multi-task post-training framework that trains a single RTL-specialized model to generate RTL, construct task-appropriate EDA checks, and revise implementations using tool feedback. The framework combines automatically constructed multi-task demonstrations with staged supervision from chain-of-thought to tool-integrated reasoning. We further introduce Pattern-Aware Policy Optimization (PAPO) for multi-task reinforcement learning. PAPO augments Group Relative Policy Optimization with correctness-gated rewards that favor concise successful checking while rewarding effective revision, and uses task grouping to preserve coverage across objectives. On CVDP, RTL-Interact-32B achieves 48.7% weighted Pass@1 and 68.9% Pass@5, surpassing its teacher model, DeepSeek-V3.2, while RTL-Interact-8B achieves 44.9% weighted Pass@1. Additionally, we show that PAPO can reduce average tool calls by 63.8% while improving Pass@1. Both models also outperform all RTL-specialized baselines on VerilogEval v2 and RTLLM v2, demonstrating the effectiveness of our method.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_1062a0438f0057afbdeb413a