用自纠错机制让开源大模型自动生成可综合的硬件代码
PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
- 多智能体协作+渐进式错误反馈，实现无人工干预的RTL生成
- 在两个开源数据集上达到顶尖通过率，且生成效率高
- 兼容开闭源模型，有效缩小二者性能差距
我们提出一种由多个智能体组成的代理流程，结合专用大语言模型与硬件仿真工具，协同完成无需人工干预的寄存器传输级（RTL）生成任务。该流程的核心是渐进式错误反馈系统（PEFA），一种利用迭代错误反馈逐步提升复杂度的自校正机制。生成的RTL包含编译检查、功能正确性验证和可综合结构。基于两个开源的自然语言到RTL数据集进行基准测试，结果表明，该方法在开源代理框架中使用开/闭源大语言模型均表现出色，有效弥合了两者间的性能差距。相比已有方法，本方案在保持高效令牌消耗的同时，实现了当前最优的通过率。
原文摘要 · Abstract (English)
We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key feature of the proposed flow is the progressive error feedback system of agents (PEFA), a self-correcting mechanism that leverages iterative error feedback to progressively increase the complexity of the approach. The generated RTL includes checks for compilation, functional correctness, and synthesizable constructs. To validate this adaptive approach to code generation, benchmarking is performed using two opensource natural language-to-RTL datasets. We demonstrate the benefits of the proposed approach implemented on an open source agentic framework, using both open- and closed-source LLMs, effectively bridging the performance gap between them. Compared to previously published methods, our approach sets a new benchmark, providing state-of-the-art pass rates while being efficient in token counts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。