RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.23466v2 Announce Type: replace-cross Abstract: Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, making long-horizon performance increasingly dependent on retrieval quality and…

aiscience

Sources

• T1RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM AgentsarXiv24 Sept, 04:00