Research map / Large language models / Agents, code and math
Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution
Shibing Mo, Jing Liu, Jianchu Xu, Ruilin Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use LLM-evolved placement order instead of WireMask-EA ordering | WireMask-EA greedy placement · ISPD2005 macro placement | HPWL: 34.04% | Improved |
| use LLM-evolved placement order instead of EGPlace ordering | EGPlace · ISPD2005 macro placement | HPWL: 14.08% | Improved |
| compare OrderPlace against EGPlace on adaptec1 | EGPlace · ISPD2005 adaptec1 | HPWL: 5.72 vs 5.75 | Hurt |
| OrderPlace vs EGPlace average rank | EGPlace · ISPD2005 macro placement | average rank: 2.50 -> 1.17 | Improved |
| use top-1 dynamic LLM strategy instead of strategy 4 | OrderPlace · ISPD2005 congestion | RUDY congestion: best standardized congestion 1.00 on six of eight benchmarks | Improved |
| use OrderPlace ordering with DreamPlace on mixed-size placement | EGPlace + DreamPlace · ISPD2005 mixed-size | average rank: 2.33 -> 2.00 | Mixed |
| use worst-case ordering instead of best-case on chain topology | greedy placement · chain topology (theory) | HPWL ratio: Omega(l) | Hurt |
Closest papers by meaning
- EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation (ICML 2025 · similarity 0.90)
- See it to Place it: Evolving Macro Placements with Vision Language Models (NeurIPS 2026 · similarity 0.89)
- Reinforcement Learning within Tree Search for Fast Macro Placement (ICML 2024 · similarity 0.88)
- Chip Placement with Diffusion Models (ICML 2025 · similarity 0.87)
- Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms (NeurIPS 2025 · similarity 0.85)
- Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
