REMORY: Learning Residual Memory for Context Compaction

  • 类型：arxiv
  • 标识：2610.11287
  • 链接：https://arxiv.org/abs/2610.11287
  • 主分类：agent
  • 形态：method
  • TLDR：Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a neural memory network that supplements the summary with a bounded sequence of soft memory tokens. Given the history and summary, the network learns to generate tokens that help a frozen LLM approximate the continuation it would produce with the full history. The tokens are conditioned on the summary and appended after it, forming an analogue of a residual connection along the sequence dimension. On SummHay, REMORY im
  • 待LLM分类：否
  • 标题中文：REMORY：学习用于上下文压缩的残差记忆
  • TLDR中文：长时程智能体压缩其历史以在有限上下文窗口内继续执行，但单一的文本摘要可能无法支撑所有后续决策。我们提出 REMORY，一种神经记忆网络，通过有界序列的软记忆 token 来补充摘要。给定历史和摘要，该网络学习生成帮助冻结 LLM 近似其在完整历史下产生的续写内容的 token。这些 token 以摘要为条件并附加在其后，构成沿序列维度的残差连接类比。在 SummHay 上，REMORY 提升了
  • 来源文件：
  • /inbox/tom/_candidates/2026-10-09-agent-rag-longcontext-candidates.json