Eluna：一个用于通过推理和任务执行实现仓库运营自动化的智能语言模型系统
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
浏览论文内容
中文总结 AI 辅助
研究针对仓库运营中SOP执行问题，提出Eluna智能体系统，它是图形引导多智能体框架，采用非对称情节蒸馏方法，在基准测试和生产应用中，微调模型表现出色，匹配或超教师模型，击败基线，在票务处理应用达94%专家一致性。
中文摘要 AI 辅助
仓库运营受标准操作程序（SOP）管理，其编码复杂的多系统决策逻辑，需在严格时间限制下可靠执行。然而，语言模型智能体缺乏执行程序合规性的机制，且在完整SOP规范引入的上下文过载下性能会下降。本文提出Eluna，一个用于可靠执行SOP的生产部署智能体系统。它是一个图形引导的多智能体框架，将SOP编码为具有渐进披露的有向无环图，并将独立任务委托给并行子智能体，每个子智能体都有持久代码执行和实时数据访问。为满足生产延迟和准确性需求，使用非对称情节蒸馏，一个强大的教师模型通过情节错误记忆得到改进，然后一个较小的学生模型在去除记忆的校正轨迹上进行微调，在不增加推理时间开销的情况下内化校正。在一个13任务基准测试和两个生产应用中，微调后的模型匹配或超过其教师模型，击败所有更大的现成基准模型，在票务处理应用中达到94%的专家一致性。
英文摘要
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.
发表机构
- Amazon.com, Inc. Fulfillment Technologies and Robotics（亚马逊公司履约技术与机器人部门）
机构由 AI 辅助整理，请以论文原文为准。
