mlsanityData to 7 Oct 2026

Cluster Workload Allocation: Semantic Soft Affinity Using Natural Language Processing

arXiv 2601.09282 ↗First posted 14 Jan 2026cs.AI cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 and presents a proof-of-concept design.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 46 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

13 of 46 references.

References · 13

  1. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  2. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  3. 2018Learning Scheduling Algorithms for Data Processing Clusterscited by 133
  4. 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
  5. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  6. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  7. 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Searchcited by 33
  8. 2025Online Scheduling for LLM Inference with KV Cache Constraintscited by 17
  9. 2021Deep Reinforcement Learning-based Methods for Resource Scheduling in Cloud Computing: A Review and Future Directionscited by 14
  10. 2025Extractive Schema Linking for Text-to-SQLcited by 13
  11. 2013Dominant Resource Fairness in Cloud Computing Systems with Heterogeneous Serverscited by 2
  12. 2015Analysis and Clustering of Workload in Google Cluster Trace based on Resource Usagecited by 2
1 more
  1. 2025Cluster Workload Allocation: A Predictive Approach Leveraging Machine Learning Efficiencycited by 1

Built on by

Not cited yet.