Research map / Architectures and efficiency / RNNs and normalization
PoMtVRS: Preference-Optimized Multi-Task Vehicle Routing Solver with Preference Gating
Dian Meng, Yaoxin Wu, Yaqing Hou, Zhiguang Cao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add PGB and preference optimization to CaDA | CaDA · 16 VRPs, VRP50 | average gap: 1.721% -> 1.405% | Improved |
| add PGB and preference optimization to CaDA | CaDA · 16 VRPs, VRP100 | average gap: 2.844% -> 2.205% | Improved |
| add PGB and preference optimization to MVMoE | MVMoE · 16 VRPs, VRP50/VRP100 | average gap: 2.227%/3.680% -> 1.809%/2.951% | Improved |
| add preference-gated block (PGB) on top of PO (ablation) | PoMtVRS(CaDA) · 16 VRPs, VRP50 | average gap: 1.579% -> 1.405% | Improved |
| add head-wise gating in PGB (ablation) | PoMtVRS(CaDA) · 16 VRPs, VRP100 | average gap: 2.241% -> 2.205% | Improved |
| add state attribute mapping in PGB (ablation) | PoMtVRS(CaDA) · 16 VRPs, VRP100 | average gap: 2.323% -> 2.205% | Improved |
| train with preference optimization instead of RL (REINFORCE) (ablation) | PoMtVRS(CaDA) · 16 VRPs, VRP50 | average gap: 1.621% -> 1.405% | Improved |
| PO with ReLD-style decoder instead of RL (ablation) | ReLD configuration · 16 VRPs, VRP50 | average gap: 1.714% -> 1.438% | Improved |
| PoMtVRS(CaDA) instead of MoSES(CaDA) | CaDA · 16 VRPs, VRP100 | average gap: 2.631% -> 2.205% | Improved |
| add PoMtVRS to CaDA | CaDA · CVRPLIB Set-X | average gap: 9.230% -> 8.326% | Improved |
| add PoMtVRS to CaDA | CaDA · Zero-shot MD, VRP50 | augmented gap: 37.571% -> 34.807% | Improved |
| add efficient active search (EAS) to PoMtVRS(CaDA) | PoMtVRS(CaDA) · 16 VRPs, 1K instances | solution quality | Improved |
Closest papers by meaning
- MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts (ICML 2024 · similarity 0.89)
- Rethinking Light Decoder-based Solvers for Vehicle Routing Problems (ICLR 2025 · similarity 0.89)
- MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver (NeurIPS 2025 · similarity 0.88)
- DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems (ICML 2024 · similarity 0.88)
- Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP (NeurIPS 2025 · similarity 0.88)
- Memory-Enhanced Neural Solvers for Routing Problems (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
