FlashMem: Distilling Intrinsic Latent Memory via Computation Reuse

Understand

The stateless architecture of Large Language Models inherently lacks the mechanism to preserve dynamic context, compelling agents to redundantly reprocess history to maintain long-horizon autonomy.

• While latent memory offers a solution, current approaches are hindered by architectural segregation, relying on auxiliary encoders that decouple memory from the reasoning backbone.
• We propose FlashMem, a framework that distills intrinsic memory directly from transient reasoning states via computation reuse.
• Leveraging the property that internal representations uniquely encode input trajectories, FlashMem identifies the last hidden state as a sufficient statistic for the interaction history.