2606.10601v1 Jun 09, 2026 math.NA

Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation

Somdatta Goswami
Somdatta Goswami
Citations: 116
h-index: 7
Anirudh Kalyan
Anirudh Kalyan
Citations: 2
h-index: 1
C. Anitescu
C. Anitescu
Citations: 7,032
h-index: 32
Xiaoying Zhuang
Xiaoying Zhuang
Citations: 138
h-index: 6
T. Rabczuk
T. Rabczuk
Citations: 756
h-index: 11
Sundararajan Natarajan
Sundararajan Natarajan
Citations: 15
h-index: 2

Generating high-quality meshes for arbitrary geometries remains a fundamental bottleneck in computational engineering, often demanding heuristic tuning and semi-manual workflows. In this paper, we introduce Dmsh, a first fully automated reinforcement learning pipeline that unifies geometric decomposition and quadrilateral mesh generation within a single learning-based framework. Dmsh decomposes the problem through three coordinated agents handling topology simplification, geometric regularization, and mesh generation. The meshing process is formulated as a Markov Decision Process and solved using a parametric Soft Actor-Critic architecture with decoupled critics, enabling efficient exploration of a hybrid discrete-continuous action space. A curriculum learning strategy ensures scalability from simple domains to highly complex geometries, suppressing seed variance. By design, the recursive decomposition enables parallel meshing of subregions, yielding globally conforming all-quadrilateral meshes without post hoc correction. Across a wide range of benchmarks, Dmsh consistently outperforms existing methods in automation, robustness, and mesh quality, establishing a new paradigm for learning-based mesh generation.

0 Citations
0 Influential
16 Altmetric
80.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!