This work presents PlaceReasoner-Beta, a verifier-guided multi-agent framework that reformulates macro placement as a closed-loop reasoning problem rather than black-box optimization, demonstrating that reasoning over spatial structure under physical-design feedback can improve end-to-end layout quality beyond proxy-objective optimization.
Abstract
Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optimize hand-crafted proxy objectives, such as estimated wirelength, and typically produce placements through one-shot numerical optimization, limiting their ability to incorporate visual layout context, codified design expertise, and downstream physical-design feedback in a unified loop. We present PlaceReasoner-Beta, a verifier-guided multi-agent framework that reformulates macro placement as a closed-loop reasoning problem rather than black-box optimization. A vision-language model (VLM) planner generates candidate placements from the floorplan image, macro specifications, and connectivity structure; a geometric verifier enforces physical legality and expert placement principles; a physical verifier refines candidates using early implementation feedback; and a post-route optimizer further improves promising layouts using final PPA. To enable reproducible evaluation, we introduce PlaceReasoner-Bench, a fully open end-to-end benchmark built from open RTL designs, EDA tools, and technology libraries. It comprises 8 designs at two aspect ratios, yielding 16 tasks with fixed floorplans and I/O assignments, so methods differ only in macro positions and orientations and are evaluated using routed PPA and DRC rather than pre-route proxies. Across the benchmark, PlaceReasoner-Beta achieves the best timing among DRC-clean methods on all square tasks, reducing post-route TNS by 61.2% at 1:1 and 53.0% at 2:1 relative to the classical baseline field. It also shortens routed wirelength on most designs despite never explicitly optimizing it, demonstrating that reasoning over spatial structure under physical-design feedback can improve end-to-end layout quality beyond proxy-objective optimization.
Results show that consistency distillation provides an effective quality-runtime tradeoff and useful initialization for downstream analytical placement in full-chip placement.
Mohammad Alijanpour Alijanpour Shalmani, J. Yuan· Electronics· 0 citations
Macro placement is a critical stage in chip physical design that substantially affects downstream implementation quality. Recent search-based methods improve existing layouts through partial reconstruction, but quality-biased or spatially restricted macro selection can limit the diversity of reconstruction proposals, p...
Biao Liu, Zhi Jin, Kai-Xuan Sun et al.· arXiv.org· 0 citations
Helix is presented, the first framework for LLM-driven algorithmic evolution of placement algorithms within a production C++ (RTL-to-GDS) flow and achieves 7 × larger fitness gains against a comparable-budget LLM single-shot baseline.
A. B. Kahng, Sayak Kundu, Bodhisatta Pramanik· 0 citations
Experiments demonstrate that FlowPlace consistently outperforms strong RLbased and search-based baselines, achieving up to 8.4% HPWL reduction on ISPD2005 benchmarks, which highlights the potential of flow-based generative models as a powerful foundation for next-generation learning-driven EDA tools.
It is found that weaker agents often fail before producing a valid artifact, whereas stronger agents increasingly fail on structural, geometric, and construction-process requirements, and CADWorld exposes a gap between general GUI competence and reliable execution of persistent, verifiable engineering workflows.
Zi-Han Dong, Yuan-Zhe Liu, Zhi-Yuan Ma et al.· 1 citation
This paper proposes a simulation-aware LLM multi-agent framework that performs in-context policy improvement (ICPI) by iteratively updating layout optimization parameters exposed by an analog layout generator through an act–observe–reflect loop on compact structured layout representations.
Bing-Yang Liu, Zi-Yu Wei, Xiao-Han Gao et al.· 2026 IEEE International Conf...· 7 citations· ⚡1