# Evolution of Optimization Algorithms for Global Placement via Large Language Models

arXiv: https://arxiv.org/abs/2504.17801 · HTML: https://mlsanity.com/paper/2504.17801/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 71 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [VerilogEval: Evaluating Large Language Models for Verilog Code Generation](https://mlsanity.com/paper/2309.07544/) (2023)
- [ChipNeMo: Domain-Adapted LLMs for Chip Design](https://mlsanity.com/paper/2311.00176/) (2023)
- [Benchmarking Large Language Models for Automated Verilog RTL Code Generation](https://mlsanity.com/paper/2212.11140/) (2022)
- [AnalogCoder: Analog Circuit Design via Training-Free Code Generation](https://mlsanity.com/paper/2405.14918/) (2024)
- [RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution](https://mlsanity.com/paper/2312.08617/) (2023)
- [A Systematic Survey on Large Language Models for Algorithm Design](https://mlsanity.com/paper/2410.14716/) (2024)
- [GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models](https://mlsanity.com/paper/2309.10730/) (2023)
- [Multi-objective Evolution of Heuristic Using Large Language Model](https://mlsanity.com/paper/2409.16867/) (2024)
- [On Joint Learning for Solving Placement and Routing in Chip Design](https://mlsanity.com/paper/2111.00234/) (2021)
- [MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning](https://mlsanity.com/paper/2211.13382/) (2022)
- [ChiPFormer: Transferable Chip Placement via Offline Decision Transformer](https://mlsanity.com/paper/2306.14744/) (2023)
- [Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework](https://mlsanity.com/paper/2403.11202/) (2024)
- [AutoDSE: Enabling Software Programmers to Design Efficient FPGA Accelerators](https://mlsanity.com/paper/2009.14381/) (2020)
- [Macro Placement by Wire-Mask-Guided Black-Box Optimization](https://mlsanity.com/paper/2306.16844/) (2023)
- [LLM for SoC Security: A Paradigm Shift](https://mlsanity.com/paper/2310.06046/) (2023)
- [Evolve Cost-aware Acquisition Functions Using Large Language Models](https://mlsanity.com/paper/2404.16906/) (2024)

## Built on by (most cited first, 6 of 6)

- [Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs](https://mlsanity.com/paper/2603.07970/) (2026)
- [See it to Place it: Evolving Macro Placements with Vision-Language Models](https://mlsanity.com/paper/2603.28733/) (2026)
- [Using Multi-modal Large Language Model to Boost Fireworks Algorithm's Ability in Settling Challenging Optimization Tasks](https://mlsanity.com/paper/2511.03137/) (2025)
- [Re2MaP: Macro Placement by Recursively Prototyping and Packing Tree-based Relocating](https://mlsanity.com/paper/2511.08054/) (2025)
- [HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design](https://mlsanity.com/paper/2604.15642/) (2026)
- [MacroAgent: Regularity-Aware Macro Legalization with LLM-Agent-Designed Contour Algorithms](https://mlsanity.com/paper/2608.24946/) (2026)

## Abstract (arXiv)

Optimization algorithms are widely employed to tackle complex problems, but designing them manually is often labor-intensive and requires significant expertise. Global placement is a fundamental step in electronic design automation (EDA). While analytical approaches represent the state-of-the-art (SOTA) in global placement, their core optimization algorithms remain heavily dependent on heuristics and customized components, such as initialization strategies, preconditioning methods, and line search techniques. This paper presents an automated framework that leverages large language models (LLM) to evolve optimization algorithms for global placement. We first generate diverse candidate algorithms using LLM through carefully crafted prompts. Then we introduce an LLM-based genetic flow to evolve selected candidate algorithms. The discovered optimization algorithms exhibit substantial performance improvements across many benchmarks. Specifically, Our design-case-specific discovered algorithms achieve average HPWL improvements of 5.05%, 5.29% and 8.30% on MMS, ISPD2005 and ISPD2019 benchmarks, and up to 17% improvements on individual cases. Additionally, the discovered algorithms demonstrate good generalization ability and are complementary to existing parameter-tuning methods.