ACRouter picks the smartest AI model per task, beating Opus-only setups by 2.6x on cost

ACRouter, a new open-source AI router, learns from execution feedback to pick the best coding model per task, cutting costs 2 ...
note

A 40-year-old chemical plant engineer's Kaggle challenge record (Week 4, OR-tools learning 1)

A 40-year-old chemical plant engineer's Kaggle challenge record, Week 4. I decided to start studying with the goal of utilizing programming in my work. This week, I continued studying on my commute. I ...
GitHub

Towards Foundation Models for Vehicle Routing Problems

Note that this project is also compatible with normal pip install -e . in case you use a different package manager. Data generation: We also include scripts to re-generate data manually (reproducible ...
Scientific Research Publishing

Comparing Modeling Approaches for Distributed Contested Logistics ()

In any military operation, reliable logistics is essential to maintaining a combat-effective force. Without the continual resupply of ammunition, food, and other materiel, forces cannot sustain their ...
IEEE

Solving Capacitated and Time-constrained Vehicle Routing Problems by Deep Reinforcement Learning-based Method

Abstract: The Capacitated and Time-Constrained Vehicle Routing Problem (CTCVRP) is regarded as a complex but essential, optimization mission in logistics and transportation systems. In this paper, we ...
IEEE

On the Split Delivery Vehicle Routing Problem Based on Python

Abstract: This paper studies the split delivery vehicle routing problem (SDVRP) with single depot, single type of vehicle, without windows, loading-unloading. Then, the three subscript mathematical ...