English

Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution

Machine Learning 2026-07-09 v1 Artificial Intelligence

Abstract

Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constraints, yet LLM agents lack mechanisms to enforce procedural compliance and degrade under the context overload full SOP specifications introduce. We present Eluna, a production-deployed agentic system for reliable SOP execution. Eluna is a graph-guided, multi-agent framework that encodes SOPs as directed acyclic graphs with progressive disclosure and delegates independent tasks to parallel sub-agents, each with persistent code execution and live data access. To meet production latency and accuracy needs, we use asymmetric episodic distillation where a strong teacher is improved through episodic error memories, then a smaller student is fine-tuned on the corrected trajectories with memory stripped, internalizing corrections without inference-time overhead. On a 13-task benchmark and two production applications, our fine-tuned models match or exceed their teacher, beat all larger off-the-shelf baselines, and reach 94% expert agreement on the ticket processing application.

Cite

@article{arxiv.2607.08960,
  title  = {Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution},
  author = {Ning Liu and Kalle Kujanpää and Zhaoxuan Zhu and P Aditya Sreekar and Kaiwen Liu and Chuanneng Sun and Jorge Marchena Menendez and Matthew Bales and Tianyu Yang and Shahnawaz Alam and Rose Yu and Baoyuan Liu and Kristina Klinkner and Shervin Malmasi},
  journal= {arXiv preprint arXiv:2607.08960},
  year   = {2026}
}