← Saturday, October 10, 2026AgentsPaper

REMORY adds learned memory tokens to compacted agent histories

huggingface.co by Hanchen Xia et al. Editor score 8/10

REMORY appends bounded soft memory tokens to a summary; on SummHay it approaches the full-context joint score using 5.2% of input positions, and it reduces repeated tool outputs and errors on agent benchmarks. This offers a measured approach to context limits in long-running agents.

What

REMORY supplements a textual history summary with a bounded sequence of learned soft memory tokens for long-horizon agents.

Method

Conditioned on the summary, its network generates tokens appended after it to help a frozen LLM approximate full-history continuation.

Why it matters

On SummHay, it approached the full-context joint score using 5.2% of input positions; agent benchmarks also showed fewer repeated tool outputs and errors.

Read on huggingface.co → Code · 2 stars

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.