vehicle routing problem
PulseAugur coverage of vehicle routing problem — every cluster mentioning vehicle routing problem across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
AI agents automate feature extractor creation for complex problems
Researchers have developed agentic approaches to automate the creation of feature extractors for constraint satisfaction problems. One method uses Large Language Models (LLMs) in a check-fix-verify loop to generate Pyth…
-
Deep Reinforcement Learning Optimizes Truck Routing, Cuts Costs by 10%
This paper explores the application of deep reinforcement learning (DRL) to solve the complex Vehicle Routing Problem (VRP) in the logistics industry. It presents a case study focusing on truck network design for three …
-
LLM-as-Trainer paradigm boosts multi-task vehicle routing solvers
Researchers have developed a novel training paradigm called LLM-as-Trainer (LaT) to improve multi-task neural solvers for the vehicle routing problem (VRP). This approach utilizes a pretrained large language model to pr…
-
New AI method drastically cuts optimization time for vehicle routing problems
Researchers have developed a new method called Learned Pairwise Deep Dual-Optimal Inequalities (L-PDDOIs) to stabilize column generation, a crucial technique for large-scale optimization problems like vehicle routing. T…
-
New heuristic matches advanced routing algorithms with vastly reduced computation
Researchers have developed a new reward-density heuristic, termed the Efficiency heuristic, for dynamic multi-vehicle routing problems. This heuristic aims to maximize cumulative reward collected by a fleet of vehicles …
-
Transformer-based ML optimizes nursing care taxi dispatch
Researchers have developed a new machine learning approach, based on the Transformer architecture, to optimize the dispatch of nursing care taxis. This method addresses complex constraints such as wheelchair use, user c…
-
RACL method enhances metaheuristic learning with reasoning agent control
Researchers have introduced RACL, a novel Reasoning-Agent Control Layer designed to enhance metaheuristic learning. RACL integrates a reasoning agent above an existing optimizer, allowing it to control the optimizer's s…
-
New vision-assisted model tackles complex vehicle routing problems
Researchers have developed a vision-assisted foundation model (VaFM) to tackle complex multi-task vehicle routing problems. This new model integrates visual information with graph-based approaches to simultaneously opti…
-
LLM constraint injection method boosts optimization modeling accuracy
Researchers have developed a new method called constraint injection to improve how large language models handle complex optimization problems. This technique addresses the issue of LLMs incorrectly adding or omitting co…
-
VRP reformulated as graph edit distance for new analysis
Researchers have reformulated the Vehicle Routing Problem (VRP) as a Graph Edit Distance (GED) maximization problem. This new approach models VRP at the edge level, allowing for deeper structural analysis of solutions a…
-
New L2R framework scales neural routing solvers to 10 million nodes
Researchers have developed a novel framework called L2R, designed to enhance the efficiency and scalability of neural combinatorial optimization for solving vehicle routing problems. This learning-based approach adaptiv…
-
New AI Model Enhances Vehicle Routing Problem Generalization
Researchers have developed a new model architecture called Residual Refined Experts with Instance-level Gating (R2E-IG) to improve the generalization capabilities of Deep Reinforcement Learning (DRL) models for Vehicle …
-
COAgents framework improves VRP solutions with multi-agent learning
Researchers have developed COAgents, a novel multi-agent framework designed to tackle complex Vehicle Routing Problems (VRPs). This framework models the search for optimal solutions as a graph, using specialized agents …
-
New training strategy enhances neural routing policies with lookahead prediction
Researchers have developed a new training strategy called Multi-node Lookahead Prediction (MnLP) to improve neural routing policies. This method addresses the limitation of current approaches that focus only on the next…
-
New neural solvers tackle complex routing problems with enhanced generalization
Researchers have developed new neural network frameworks to address complex routing problems, aiming for greater generalization across different problem types. SPACE unifies symmetric and asymmetric vehicle routing prob…
-
New CARM module boosts neural routing solver performance
Researchers have developed a new module called Constraint-Aware Residual Modulation (CARM) to improve the performance of neural routing solvers. Existing solvers often struggle with complex constraints because their sta…
-
New NEPF method tackles scalable routing for complex vehicle problems
Researchers have developed a new method called Two-Stage Learned Decomposition for Scalable Routing on Multigraphs (NEPF) to address limitations in existing neural approaches for the Vehicle Routing Problem (VRP). This …
-
New NEPF method tackles scalable routing for complex vehicle problems
Researchers have developed a new method called Node-Edge Policy Factorization (NEPF) to address the scalability issues in solving Vehicle Routing Problems (VRPs) on multigraphs. This approach decomposes the routing poli…
-
Quantum reinforcement learning with QAOA enhances vehicle routing optimization
Researchers have developed a novel hybrid approach integrating the Quantum Approximate Optimization Algorithm (QAOA) into a Quantum Reinforcement Learning (QRL) policy network. This integration allows the agent to lever…
-
Vehicle routing systems face scaling bottlenecks beyond algorithms
A user experimenting with scaling vehicle routing problems to approximately one million stops discovered that system architecture, rather than the routing algorithm itself, became the primary bottleneck. Key factors inf…