SOURCE-LINKED INTELLIGENCE

Memory Control Signals Emerge Before Action in Long Horizon Agents

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder to preserve and reuse. Existing context management methods mainly focus on how to compress or retrieve history, but largely leave open whether the model itself already represents the need for these memory operations before they occur. We study the hidden state immediately before each agent action and find that compression and recall needs are already encoded in the model's internal representations. These signals cannot be explained by simple con

Read original source ↗ Open in workspace

recordType

paper

region

Global