{"total":14,"rows":[{"id":"2603.26796","title":"Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2606.20898","title":"The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2609.01572","title":"From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2509.22211","title":"LogiPart: Local Large Language Models for Data Exploration at Scale with Logical Partitioning","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.14908","title":"On-Premise SLMs vs. Commercial LLMs: Prompt Engineering and Incident Classification in SOCs and CSIRTs","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2601.08844","title":"Emissions and Performance Trade-off Between Small and Large Language Models","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2602.20513","title":"From Performance to Purpose: A Sociotechnical Taxonomy for Evaluating Large Language Model Utility","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.14969","title":"Discovering Novel LLM Experts via Task-Capability Coevolution","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.29280","title":"Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.13239","title":"Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.04488","title":"Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.07148","title":"A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2610.04956","title":"From Overloaded to Guaranteed: High-Throughput Multi-SLO Enforcement for LoRA-Assisted On-Premise LLM Deployment","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.09778","title":"Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression Testing","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}