# MappingEvolve: LLM-Driven Code Evolution for Technology Mapping

arXiv: https://arxiv.org/abs/2604.26591 · HTML: https://mlsanity.com/paper/2604.26591/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 32 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 3 of 3)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Physically Aware Synthesis Revisited: Guiding Technology Mapping with Primitive Logic Gate Placement](https://mlsanity.com/paper/2408.07886/) (2024)

## Built on by (most cited first, 3 of 3)

- [Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks](https://mlsanity.com/paper/2606.01975/) (2026)
- [Agentic Electronic Design Automation: A Handoff Perspective](https://mlsanity.com/paper/2606.19795/) (2026)
- [AgenticPD: A Stage-Aware Agentic Framework for Physical Design QoR Optimization](https://mlsanity.com/paper/2607.04758/) (2026)

## Abstract (arXiv)

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