Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
Paper LLMs & Texto

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

Agent Memory Distillation improves small language model tool-use performance by transferring structured hierarchical memory from a large teacher agent without additional training.

Hugging Face · Daily Papers ·Taeil Kim, Kangsan Kim · ·▲ 26 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Taeil Kim, Kangsan Kim, Sung Ju Hwang

  • 26 upvotes da comunidade
  • Temas: Agent Memory Distillation, hierarchical memory, Workflow memory, Subtask memory, Function memory, tool-calling errors

Resumo

Resumo original (em inglês), extraído do paper:

Agent Memory Distillation improves small language model tool-use performance by transferring structured hierarchical memory from a large teacher agent without additional training.

Onde ler

compartilhar: