SmartRAG：用于移动设备的基于原生图的RAG
SmartRAG: Native Graph-Based RAG for Mobile Device
浏览论文内容
中文总结 AI 辅助
研究针对移动设备部署大语言模型的问题，提出SmartRAG框架，围绕四个模块组织智能助手，核心是可持续学习的EvoNER，知识存于MRGraph，通过混合管道检索，实验表明其在多跳推理性能上有竞争力且能在普通智能手机上运行。
中文摘要 AI 辅助
在移动设备上部署大语言模型作为个人助手需要隐私、低延迟和离线可用性，但巨型模型的计算成本与严格的边缘硬件预算相冲突。我们认为仅靠模型压缩无法解决这种矛盾，需要将设备上的智能分解为互补的功能角色。我们提出了SmartRAG，这是一个完全在设备上的框架，围绕四个协调模块——感知、记忆、聚焦和思考来组织智能助手。SmartRAG的核心是EvoNER，它是一个可持续学习的命名实体识别器，通过教师提炼更新逐步扩展其标签库。提取的知识存储在MRGraph中，并在查询时通过结合图遍历、词汇匹配和密集语义搜索的混合管道进行检索。仅在高价值语义操作时调用设备上的大语言模型，以限制推理成本。在四个问答基准测试上的实验表明，具有量化的17亿参数主干的SmartRAG实现了与高达18倍大的模型具有竞争力的多跳推理性能，同时完全在普通智能手机上运行，内存和延迟在实际范围内。
英文摘要
Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets. We argue that this tension cannot be resolved by model compression alone; it requires decomposing on-device intelligence into complementary functional roles. We present SmartRAG, a fully on-device framework that organizes an intelligent assistant around four coordinated modules -- Perception, Memory, Focus, and Thinking. At the core of SmartRAG is EvoNER, a continually learnable named-entity recognizer that incrementally expands its label inventory through teacher-distilled updates, enabling the system to absorb previously unseen entity types without retraining the backbone LLM. Extracted knowledge is stored in MRGraph, a three-layer provenance-preserving knowledge graph, and retrieved at query time through a hybrid pipeline combining graph traversal, lexical matching, and dense semantic search. The on-device LLM is invoked only for high-value semantic operations -- labeling, planning, and answer synthesis -- keeping inference costs bounded. Experiments on four QA benchmarks (TriviaQA, Natural Questions, HotpotQA, MultiHopQA) show that SmartRAG with a quantized 1.7B-parameter backbone achieves multi-hop reasoning performance competitive with models up to 18$\times$ larger, while running entirely on commodity smartphones within practical memory and latency envelopes.
发表机构
- Nanjing University（南京大学）
- HUST（华中科技大学）
- Southeast University（东南大学）
机构由 AI 辅助整理，请以论文原文为准。
