This paper introduces the first \emph{self-evolving} logic synthesis framework, which leverages Large Language Model (LLM) agents to autonomously improve the source code of \textsc{ABC}, the widely adopted logic synthesis system. Our framework operates on the \emph{entire integrated ABC codebase}, and the output repository preserves its single-binary execution model and command interface. In the initial evolution cycle, we bootstrap the system using existing prior open-source synthesis components, covering flow tuning, logic minimization, and technology mapping, but without manually injecting new heuristics. On top of this foundation, a team of LLM-based agents iteratively rewrites and evolves specific sub-components of ABC following our ``programming guidance`` prompts under a unified correctness and QoR-driven evaluation loop. Each evolution cycle proposes code modifications, compiles the integrated binary, validates correctness, and evaluates quality-of-results (QoR) on \emph{multi-suite benchmarks including ISCAS~85/89/99, VTR, EPFL, and IWLS~2005}. Through continuous feedback, the system discovers optimizations beyond human-designed heuristics, effectively \emph{learning new synthesis strategies} that enhance QoR. We detail the architecture of this self-improving system, its integration with \textsc{ABC}, and results demonstrating that the framework can autonomously and progressively improve EDA tool at full million-line scale.

翻译：本文提出了首个自进化逻辑综合框架，该框架利用大型语言模型（LLM）智能体自主改进广泛使用的逻辑综合系统\textsc{ABC}的源代码。我们的框架作用于\textit{整个集成的ABC代码库}，输出代码库保留其单一二进制执行模型和命令接口。在初始进化周期中，我们利用现有开源综合组件启动系统，涵盖流程调优、逻辑最小化和技术映射，但无需手动注入新的启发式方法。在此基础之上，一组基于LLM的智能体按照我们的“编程指导”提示，在统一的正确性和质量导向结果（QoR）评估循环下迭代重写并进化ABC的特定子组件。每个进化周期提出代码修改建议、编译集成二进制文件、验证正确性并在\textit{多套基准测试集（包括ISCAS~85/89/99、VTR、EPFL和IWLS~2005）}上评估质量结果（QoR）。通过持续反馈，系统发现了超越人类设计的启发式方法的优化，有效\textit{学会提升QoR的新综合策略}。我们详细描述了这一自改进系统的架构、与\textsc{ABC}的集成过程，并展示了该框架能够在全百万行代码规模上自主且渐进地改进EDA工具的结果。