Memory as a persistence channel

How often do instructions, injected or self-generated, survive in an agent's memory and summaries to act in later sessions?

assistant-draftedPrompt injectionMonitoring & control

Signals

Why it matters

Long-running agents compress their own history. Anything that survives compression carries authority it may not deserve.

Hypothesis

Summaries preserve instruction-like text at higher rates than other content, and provenance tagging reduces it.

A first study

Seed synthetic instructions into long agent sessions, run compaction, and measure survival and effect with and without provenance tags.

Controls it would need

Synthetic tasks; fixed compaction settings; blind scoring of effects.

What it could and could not claim

Would describe tested memory designs, not deployed products.