用双空间蒸馏让小模型在手机上也能高效完成复杂任务
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation
- 通过上下文和参数双重蒸馏，将大模型能力迁移到小模型
- 40亿参数模型任务成功率从4.3%提升至77.9%，接近720亿参数大模型
- 仅增加1000万可训练参数，适合实时边缘设备部署
基于大语言模型的智能体可通过多轮交互解决复杂程序化任务，但通常依赖大模型、长上下文和多次推理调用，难以在资源受限设备上部署。本文提出DuoMem，一种双空间蒸馏框架，将大教师模型的程序化问题求解能力迁移至紧凑的学生模型。DuoMem在两个互补空间进行蒸馏：(1) 上下文空间蒸馏，用教师生成的高质量程序化记忆替换学生生成的记忆并前置到输入；(2) 参数空间蒸馏，对轻量级LoRA适配器在成功教师轨迹上进行微调。在ALFWorld这一具身决策挑战基准上，DuoMem将40亿参数模型的任务成功率从4.3%提升至77.9%，接近720亿参数教师模型（87.1%），同时仅增加不到1000万可训练参数和几兆字节预计算的教师记忆。此外，增强后的40亿参数模型比720亿教师模型在真实时间上快3倍以上，具备实时边缘部署可行性。跨8个20亿-720亿参数模型的大量消融实验表明，两种蒸馏机制贡献互补。
原文摘要 · Abstract (English)
Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typically depends on large models, long contexts, and repeated inference calls. This makes advanced memory-augmented agents difficult to deploy on resource-constrained devices. We introduce DuoMem, a dual-space distillation framework that transfers procedural problem-solving ability from a large teacher model to compact student models. DuoMem distils in two complementary spaces: (1)context-space distillation, which replaces student-generated memories with higher-quality teacher-generated procedural memories prepended to the student's input, and (2)parameter-space distillation, which fine-tunes lightweight LoRA adapters on successful teacher trajectories. Evaluated on ALFWorld, a challenging embodied decision-making benchmark, DuoMem boosts a 4B-parameter model from 4.3% to 77.9% task success rate, closing most of the gap to a 72B teacher model (87.1%), while adding fewer than 10M trainable parameters and only a few megabytes of pre-computed teacher memories. Moreover, the DuoMem-enhanced 4B model completes tasks over 3x faster than the 72B teacher in wall-clock time, making it viable for real-time edge deployment, which would be challenging for the teacher.Extensive ablations across eight models spanning 2B-72B parameters reveal that both distillation axes contribute complementary
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。