Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

• 类型：arxiv
• 标识：2608.07169
• 链接：https://arxiv.org/abs/2608.07169
• 主分类：agent
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：Agent Memory Distillation (AMD), a training-free framework that transfers structured knowledge from a large teacher agent to a small student agent through hierarchical memory, is proposed, which consistently outperforms existing memory-based baselines.
• 待LLM分类：否
• 标题中文：Agent 记忆蒸馏：通过层级教师记忆赋能小型 LLM Agent
• TLDR中文：本文提出 Agent Memory Distillation (AMD)，一个无需训练、通过分层记忆将结构化知识从大型教师智能体迁移到小型学生智能体的框架，一致优于现有基于记忆的基线方法。
• 来源文件：
• /inbox/tom/_candidates/2026-08-11-agent-rag-longcontext-candidates.json
• [S2 enrich]