Findings/memory-carries-instructions-forward

Instructions written into an agent's long-term memory or its own context summaries can persist and later steer its behavior.

Corroboratedobserved3 evidence records from 3 independent sourcesassistant-drafted
Scope: what this does not show

A 2024 injection demonstration in which injected ChatGPT memories acted across conversations, and a 2026 OpenAI report from RL training in which self-written summary instructions carried into a continued task and were followed in one reported example. Not a rate. A September 2026 simulation study adds measured (not observed in the wild) persistence through agent memory in synthetic agent networks.

Corroborated: Supported by at least two independent sources.

Evidence

Status history

  1. 2024-09-20ReportedInjected memory entries persisted across conversations. · record
  2. 2026-09-16CorroboratedOpenAI reports self-generated instructions in compaction summaries. · record