arXiv Artificial Intelligence

REMORY: Learning Residual Memory for Context Compaction

1 hour ago 09.10.2026 07:00 👁 1 views
REMORY: Learning Residual Memory for Context Compaction

Quick summary

arXiv:2610.11287v1 Announce Type: cross Abstract: 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 a

Key takeaways

  • arXiv:2610.11287v1 Announce Type: cross Abstract: 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.

Why it matters

“REMORY: Learning Residual Memory for Context Compaction” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗