Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

  • 类型:arxiv
  • 标识:2609.27334
  • 链接:https://arxiv.org/abs/2609.27334
  • 主分类:agent
  • 形态:method
  • TLDR:Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory is distilled into a fixed artifact, such as a reflection, workflow, skill, or reasoning strategy, that is later retrieved by similarity. This forces the system to decide what is worth remembering before the future query is known, irreversibly discarding information and producing a query-independent summary that must serve many possible downstream tasks. Learning such a write-time curator is also difficult because the value o
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-09-24-agent-rag-longcontext-candidates.json