# Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement

arXiv: https://arxiv.org/abs/2608.13767 · HTML: https://mlsanity.com/paper/2608.13767/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning](https://mlsanity.com/paper/2308.13724/) (2023)
- [Large Language Models Can Self-Improve At Web Agent Tasks](https://mlsanity.com/paper/2405.20309/) (2024)
- [Internal Consistency and Self-Feedback in Large Language Models: A Survey](https://mlsanity.com/paper/2407.14507/) (2024)
- [ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models](https://mlsanity.com/paper/2406.18770/) (2024)
- [SelfEvolve: A Code Evolution Framework via Large Language Models](https://mlsanity.com/paper/2306.02907/) (2023)
- [LayoutCopilot: An LLM-powered Multi-agent Collaborative Framework for Interactive Analog Layout Design](https://mlsanity.com/paper/2406.18873/) (2024)
- [LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuits](https://mlsanity.com/paper/2411.12930/) (2024)
- [Autonomous Code Evolution Meets NP-Completeness](https://mlsanity.com/paper/2509.07367/) (2025)
- [AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing](https://mlsanity.com/paper/2511.03697/) (2025)
- [TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits](https://mlsanity.com/paper/2509.14169/) (2025)
- [LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit](https://mlsanity.com/paper/2504.11497/) (2025)
- [ChatPattern: Layout Pattern Customization via Natural Language](https://mlsanity.com/paper/2403.15434/) (2024)
- [PANDA: An LLM-Enhanced Performance-Driven Analog Design Framework Bridging Design Intent and Layout Generation](https://mlsanity.com/paper/2606.15052/) (2026)

## Abstract (arXiv)

Analog IC layout design remains a labor-intensive iterative process dominated by simulation-driven refinement. Although end-to-end layout generators accelerate initial placement and routing, they still require experts to manually tune layout optimization parameters with repeated post-layout simulations for stringent design specifications. While Bayesian Optimization (BO) is widely adopted for parameter tuning in analog IC design, at the layout level it typically requires hundreds to thousands of evaluations, each involving costly parasitic extraction and post-layout simulation, which makes it impractical. Recently, Large Language Models (LLMs) have demonstrated potential in improving the sample efficiency of such simulation-driven tuning. However, their restricted access to geometric layout context and design-specific heuristics limits their ability to manipulate the layout optimization process. In this paper, we propose 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. Experiments on real-world analog circuits show that, with only tens of post-layout simulations, our approach improves post-layout performance over the generator's built-in heuristics and BO-based tuning method.