Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.18094 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911693910573056 |
|---|---|
| author | Fan, Mingfeng Zhou, Jianan Cheng, Jiaqi Zhang, Yifeng Zhang, Jie Sartoretti, Guillaume Adrien |
| author_facet | Fan, Mingfeng Zhou, Jianan Cheng, Jiaqi Zhang, Yifeng Zhang, Jie Sartoretti, Guillaume Adrien |
| contents | We study the Compositional Geometry Routing Problem (CGRP), a unified superclass of traditional routing problems that covers point-only, line-only, area-only, and arbitrary hybrid task geometries, providing a broad abstraction for real-world routing scenarios. Beyond standard point-based routing, CGRP with non-point tasks can be inherently asymmetric, tightly coupled travel routes with the intrinsic path, and enlarges the action space with numerous feasible yet often irrelevant options, thereby posing significant challenges for both representation learning and decision-making. To address these challenges, we propose DiCon, a differential attention-assisted solver with contrastive learning, as a plug-and-play framework that tackles the problem from two complementary angles. First, we introduce a differential attention mechanism that actively suppresses the probability mass on less competitive candidate actions. Second, we design a double-level contrastive learning objective to promote robust global instance representations and regularize geometry-aware task representations. Extensive experiments demonstrate that DiCon achieves strong performance, broad versatility, and superior generalization across diverse CGRP instances with different compositions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18094 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Solve Compositional Geometry Routing Problems Fan, Mingfeng Zhou, Jianan Cheng, Jiaqi Zhang, Yifeng Zhang, Jie Sartoretti, Guillaume Adrien Artificial Intelligence We study the Compositional Geometry Routing Problem (CGRP), a unified superclass of traditional routing problems that covers point-only, line-only, area-only, and arbitrary hybrid task geometries, providing a broad abstraction for real-world routing scenarios. Beyond standard point-based routing, CGRP with non-point tasks can be inherently asymmetric, tightly coupled travel routes with the intrinsic path, and enlarges the action space with numerous feasible yet often irrelevant options, thereby posing significant challenges for both representation learning and decision-making. To address these challenges, we propose DiCon, a differential attention-assisted solver with contrastive learning, as a plug-and-play framework that tackles the problem from two complementary angles. First, we introduce a differential attention mechanism that actively suppresses the probability mass on less competitive candidate actions. Second, we design a double-level contrastive learning objective to promote robust global instance representations and regularize geometry-aware task representations. Extensive experiments demonstrate that DiCon achieves strong performance, broad versatility, and superior generalization across diverse CGRP instances with different compositions. |
| title | Learning to Solve Compositional Geometry Routing Problems |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.18094 |