Cluster workload allocation often requires complex configurations, creating a usability gap. This paper introduces a semantic, intent-driven scheduling paradigm for cluster systems using Natural Language Processing. The system employs a Large Language Model (LLM) integrated via a Kubernetes scheduler extender to interpret natural language allocation hint annotations for soft affinity preferences. A prototype featuring a cluster state cache and an intent analyzer (using AWS Bedrock) was developed. Empirical evaluation demonstrated high LLM parsing accuracy (>95% Subset Accuracy on an evaluation ground-truth dataset) for top-tier models like Amazon Nova Pro/Premier and Mistral Pixtral Large, significantly outperforming a baseline engine. Scheduling quality tests across six scenarios showed the prototype achieved superior or equivalent placement compared to standard Kubernetes configurations, particularly excelling in complex and quantitative scenarios and handling conflicting soft preferences. The results validate using LLMs for accessible scheduling but highlight limitations like synchronous LLM latency, suggesting asynchronous processing for production readiness. This work confirms the viability of semantic soft affinity for simplifying workload orchestration.
Yifei Shen, Yilun Zhao +3
Real-world clinical text-to-SQL requires reasoning over heterogeneous EHR tables, temporal windows, and patient-similarity cohorts to produce executable queries. We introduce CLINSQL, a benchmark of 6...
Ebubekir Tosun, Mehmet Emin Buldur +2
Neural embeddings have a notorious blind spot: they can't reliably tell synonyms apart from antonyms. Consequently, increasing similarity thresholds often fails to prevent opposites from being grouped...
Ebubekir Tosun, Mehmet Emin Buldur +2
We present a hybrid methodology for generating large-scale semantic relationship datasets in low-resource languages, demonstrated through a comprehensive Turkish semantic relations corpus. Our approac...
Mara Finkelstein, Isaac Caswell +18
We present TranslateGemma, a suite of open machine translation models based on the Gemma 3 foundation models. To enhance the inherent multilingual capabilities of Gemma 3 for the translation task, we ...
Yahya Masri, Emily Ma +3
System logs are crucial for monitoring and diagnosing modern computing infrastructure, but their scale and complexity require reliable and efficient automated interpretation. Since severity levels are...
