Zero-Mem: Zero-Token Memory Operations for LLM Agents

  • 类型:arxiv
  • 标识:2607.29377
  • 链接:https://arxiv.org/abs/2607.29377
  • 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:The results show that structured agent memory need not generate an intermediate representation of the past, and Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations.
  • 待LLM分类:否
  • 标题中文:标题 -> 标题中文:Zero-Mem:面向 LLM Agent 的零 token 记忆操作
  • TLDR中文:结果表明结构化 agent 记忆无需生成过去的中间表示,Zero-Mem 在消除记忆操作中 LLM 调用与 LLM-token 消耗的同时取得具有竞争力的性能
  • 来源文件
  • /inbox/tom/_candidates/2026-08-05-agent-rag-longcontext-candidates.json
  • [S2 enrich]