# Enhancing Reinforcement Learning for the Floorplanning of Analog ICs with Beam Search

arXiv: https://arxiv.org/abs/2505.05059 · HTML: https://mlsanity.com/paper/2505.05059/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 4 of 4)

- [Simulation-guided Beam Search for Neural Combinatorial Optimization](https://mlsanity.com/paper/2207.06190/) (2022)
- [MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning](https://mlsanity.com/paper/2211.13382/) (2022)
- [Fast ML-driven Analog Circuit Layout using Reinforcement Learning and Steiner Trees](https://mlsanity.com/paper/2405.16951/) (2024)
- [Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning](https://mlsanity.com/paper/2411.15212/) (2024)

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

- [OSIRIS: Bridging Analog Circuit Design and Machine Learning with Scalable Dataset Generation](https://mlsanity.com/paper/2601.19439/) (2026)
- [Inspector: Conversational and Lightweight Analyzer of Analog Circuit Layouts Using LLM and CNNs](https://mlsanity.com/paper/2609.34976/) (2026)
- [THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout](https://mlsanity.com/paper/2609.35035/) (2026)

## Abstract (arXiv)

The layout of analog ICs requires making complex trade-offs, while addressing device physics and variability of the circuits. This makes full automation with learning-based solutions hard to achieve. However, reinforcement learning (RL) has recently reached significant results, particularly in solving the floorplanning problem. This paper presents a hybrid method that combines RL with a beam (BS) strategy. The BS algorithm enhances the agent's inference process, allowing for the generation of flexible floorplans by accomodating various objective weightings, and addressing congestion without without the need for policy retraining or fine-tuning. Moreover, the RL agent's generalization ability stays intact, along with its efficient handling of circuit features and constraints. Experimental results show approx. 5-85% improvement in area, dead space and half-perimeter wire length compared to a standard RL application, along with higher rewards for the agent. Moreover, performance and efficiency align closely with those of existing state-of-the-art techniques.