LaT: LLM-as-Trainer for Multi-Task Vehicle Routing Solvers

• URL: http://arxiv.org/abs/2607.17708v1
• Date: Mon, 20 Jul 2026 09:02:11 GMT
• Title: LaT: LLM-as-Trainer for Multi-Task Vehicle Routing Solvers
• Abstract summary: LLM-as-Trainer (LaT) is a plug-and-play training paradigm that uses a pretrained large language model as an external trainer.<n>LaT periodically analyzes cross-task validation metrics to generate a stage-wise guidance vector.<n>Experiments on 16 VRP variants show that LaT improves the solution quality of several state-of-the-art multi-task neural solvers on both trained and unseen variants.
• Score: 38.3136053148872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-task neural solvers aim to handle multiple Vehicle Routing Problem (VRP) variants within a unified model, avoiding separate training for each constraint combination. However, VRP variants differ in optimization difficulty, while existing methods lack stage-wise feedback on their training status, making the model biased to some specific variants. Although meta-learning can support adaptive training, it typically requires bi-level optimization and additional gradient updates, increasing computational cost. To address this limitation, we propose LLM-as-Trainer (LaT), a plug-and-play training paradigm that uses a pretrained large language model as an external trainer. LaT periodically analyzes cross-task validation metrics to generate a stage-wise guidance vector. This vector is combined with the current task's constraint vector and injected into each encoder layer, providing the neural solver with additional training information during subsequent policy optimization. Experiments on 16 VRP variants show that LaT improves the solution quality of several state-of-the-art multi-task neural solvers on both trained and unseen variants, supporting the effectiveness and generality of the proposed training paradigm.

Related papers

• MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous Driving [12.330414519761524]
  Trajectory planning is a core task in autonomous driving.<n>MLLMs with Reinforcement Learning have shown promise in addressing "long-tail" scenarios.<n>We present MTDrive, a multi-turn framework that enables MLLMs to iteratively refine trajectories based on environmental feedback.
  arXiv  Detail & Related papers  (2026-01-30T12:47:55Z)
• Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter [52.111923076688505]
  Training Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving.<n>We propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding.
  arXiv  Detail & Related papers  (2025-11-20T18:59:25Z)
• MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver [20.386780842875442]
  This work introduces a novel multi-task learning method driven by knowledge distillation (MTL-KD)<n>The proposed MTL-KD method transfers policy knowledge from multiple distinct RL-based single-task models to a single heavy decoder model, label-free training and effectively improving the model's generalization ability across diverse tasks.<n> Experimental results on 6 seen and 10 unseen VRP variants with up to 1000 nodes indicate that our proposed method consistently achieves superior performance on both uniform and real-world benchmarks.
  arXiv  Detail & Related papers  (2025-06-03T14:35:36Z)
• Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning [5.948751929134844]
  We introduce a novel learning framework driven by Large Language Models (LLMs)<n>Unlike prevailing techniques that necessitate joint training with the neural network, our approach operates exclusively during the inference phase.<n>Our method enables a backbone model (trained on 100-node instances) to achieve superior performance on large-scale Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) of up to 100K nodes from diverse distributions.
  arXiv  Detail & Related papers  (2025-06-03T03:15:22Z)
• AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs [68.99086112477565]
  Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation.<n>Existing heterogeneous training methods significantly expand the scale of trainable models but introduce substantial communication overheads and CPU workloads.<n>We propose AutoHete, an automatic and efficient heterogeneous training system compatible with both single- GPU and multi- GPU environments.
  arXiv  Detail & Related papers  (2025-02-27T14:46:22Z)
• ATE-SG: Alternate Through the Epochs Stochastic Gradient for Multi-Task Neural Networks [44.99833362998488]
  This paper introduces novel alternate training procedures for hard- parameter sharing Multi-Task Neural Networks (MTNNs)<n>The proposed alternate training method updates shared and task-specific weights alternately through the epochs, exploiting the multi-head architecture of the model.<n> Empirical experiments demonstrate enhanced training regularization and reduced computational demands.
  arXiv  Detail & Related papers  (2023-12-26T21:33:03Z)
• Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization [35.09656455088854]
  We propose an efficient meta neural vector (EMNH) to solve multi-objective optimization problems. EMNH is able to outperform the state-of-the-art neurals in terms of solution quality and learning efficiency.
  arXiv  Detail & Related papers  (2023-10-22T08:59:02Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)
• UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers [108.92194081987967]
  We make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks. Unlike previous RNN-based models, we utilize a transformer-based model to generate a flexible policy. The proposed model, named as Universal Policy Decoupling Transformer (UPDeT), further relaxes the action restriction and makes the multi-agent task's decision process more explainable.
  arXiv  Detail & Related papers  (2021-01-20T07:24:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.