arXiv AI July 16, 2026 By Xi Cheng, Ke Liu, Siyuan Feng, Jane Lin, H. Oliver Gao

Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management

arXiv:2607. 13239v1 Announce Type: new Abstract: Foundation models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used for transportation management center (TMC) tasks such as anomaly detection, incident reporting, and traveler information.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 8

Scalable Joint Resource Allocation for SLO-Constrained LLM Inference in Heterogeneous GPU Clouds

arXiv:2604. 07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism configuration, and workload routing under latency, accuracy, memory, and budget constraints.

By Jiaming Cheng, Duong Tung Nguyen

llms

arXiv AI

Jul 8

Reward-Density Heuristic for Dynamic Multi-Vehicle Routing: Performance and Computational Efficiency

arXiv:2607. 06066v1 Announce Type: new Abstract: The Vehicle Routing Problem (VRP) and its variants represent some of the most practically consequential optimization challenges in modern logistics and urban mobility.

By Manish Kolachalam, Rani Malhotra

agents robotics

arXiv AI

Jul 7

Robust Feasible Route Construction through Collaborative Partition Optimization

arXiv:2607. 03694v1 Announce Type: new Abstract: Large-scale Capacitated Vehicle Routing Problems (CVRPs) are commonly solved by partitioning customers into smaller routing problems that can be optimized independently.

By Oguzhan Karaahmetoglu, Hyong Kim

benchmarks

arXiv AI

Jul 16

Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs

arXiv:2607. 13080v1 Announce Type: cross Abstract: Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-premise quantized open-weights models, which promise low-marginal-cost scaling and data sovereignty at some loss of reasoning fidelity.

By Sheng-Wei Peng, Yi-Hsun Lin, Yi-Pei Lee

llms agents efficiency

arXiv Machine Learning

Aug 13

Lifecycle-Optimal Tokenization: Vocabulary Size as a Deployment-Regime-Dependent Infrastructure Parameter

arXiv:2608. 11361v1 Announce Type: new Abstract: Tokenizer vocabulary size is a foundational design choice in large language model (LLM) infrastructure, yet it is typically fixed at training time based on convention rather than deployment analysis.

By Rima Mittal, Ankit Gubrani, Satyanarayana Kakollu

llms nlp

arXiv AI

Jun 12

Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm

arXiv:2606. 13241v1 Announce Type: new Abstract: Defining query difficulty is one of the hardest problems in deployment engineering.

By Francesco Massa, Marco Cristofanilli

llms multimodal benchmarks

Related stories

Scalable Joint Resource Allocation for SLO-Constrained LLM Inference in Heterogeneous GPU Clouds

Reward-Density Heuristic for Dynamic Multi-Vehicle Routing: Performance and Computational Efficiency

Robust Feasible Route Construction through Collaborative Partition Optimization

Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs

Lifecycle-Optimal Tokenization: Vocabulary Size as a Deployment-Regime-Dependent Infrastructure Parameter

Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm