Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
For warehouse operations, Eluna provides a reliable and accurate system for executing complex SOPs, addressing the problem of LLM agents failing under procedural compliance and context overload.
Eluna is a production-deployed agentic system for warehouse SOP execution that uses graph-guided multi-agent framework and asymmetric episodic distillation, achieving 94% expert agreement on ticket processing and matching or exceeding larger baselines.
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.