MappingEvolve: LLM-Driven Code Evolution for Technology Mapping

arXiv cs.AI / 4/30/2026

📰 NewsDeveloper Stack & InfrastructureIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces MappingEvolve, an open-source framework that uses LLMs to evolve the core code behind technology mapping in logic synthesis rather than only generating optimization scripts.
MappingEvolve breaks the mapping problem into distinct optimization operators and uses a hierarchical agent architecture (Planner, Evolver, Evaluator) to guide an evolutionary search over code changes.
Experiments on EPFL benchmarks show substantial gains, including 10.04% area reduction versus ABC and 7.93% versus mockturtle.
The method reports strong overall score improvements (46.6%–96.0% S_overall) while explicitly managing the area–delay trade-off.
The framework’s code and data are released on GitHub, enabling others to reproduce and build on the approach.

Abstract

Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimization scripts, their potential for core algorithm enhancement remains untapped. We introduce MappingEvolve, an open-source framework that pioneers the use of LLMs to directly evolve technology mapping code. Our method abstracts the mapping process into distinct optimization operators and employs a hierarchical agent-based architecture, comprising a Planner, Evolver, and Evaluator, to guide the evolutionary search. This structured approach enables strategic and effective code modifications. Experiments show our method significantly outperforms direct evolution and strong baselines, achieving 10.04\% area reduction versus ABC and 7.93\% versus mockturtle, with 46.6\%--96.0\%

S_{overall}

improvement on EPFL benchmarks, while explicitly navigating the area--delay trade-off. Our code and data are available at https://github.com/Flians/MappingEvolve.