GPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed Placement

Design Space Exploration of Reinforcement Learning Configurations for Post-Legalization Placement

Improving chip macro placement via GFlowNet-guided tree search

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.

From Connectivity to Rewards: Dense Reward Learning with Directed State Graphs

This paper introduces a state connectivity model designed to predict pairwise state connectivity strength in asymmetric environments, and transforms these connectivity strengths into scalar auxiliary dense rewards, providing continuous guidance across multiple hierarchical levels.

A Center-Guided Reinforcement Learning Method for Hyperparameter Optimization and Its Application to Relation Extraction

The effectiveness of CGRL for limited-budget HPO and its applicability to practical RE tasks are demonstrated and a process-aware reward provides dense and informative feedback for policy learning.

Expert-Space Exploration in MoE Reinforcement Learning

ESRL is introduced, an architecture-aware framework that explicitly explores the expert-routing space of MoE models, and preserves high-confidence experts as anchors, and restricts stochastic routing to a plausible candidate pool, thereby retaining reliable computation paths.

Deep Reinforcement Learning on Item-Compatibility Graphs for One-Dimensional Bin Packing

A novel end-to-end, size-agnostic graph reinforcement learning framework for 1D-BPP that outperforms a state-of-the-art learned solver that relies on column generation and integer programming, while using no solver at all.