# KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents

> Source: <https://www.machinebrief.com/news/keeper-learning-control-sufficient-textual-memory-for-long-h-jxju>
> Published: 2026-11-02 05:00:00+00:00

arXiv:2610.41482v1 Announce Type: new 
Abstract: Recursive textual memory can carry earlier errors into later updates, yet task performance alone does not establish memory reliability. We define self-consistency bias as the persistence of incorrect claims already present in the incoming memory. We present KEEPER, a comparative analysis of four auxiliary objectives along information-content and update-sensitivity axes within a shared recursive interface, examining how supervision targets relate to agent performance. Among evaluated conditions, reward-related prediction achieve the highest task performance before and after offline reinforcement learning, outperforming joint supervision. A claim-level analysis of one baseline trajectory documents error persistence despite corrective observations. Together, these analyses motivate evaluating error persistence and valid-information retention alongside task outcomes.