mlsanityData to 14 Oct 2026

MoM: Memory of Memory

arXiv 2609.25054 ↗First posted 7 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

For a long-horizon LLM agent, the memory question is not what was once recorded but what currently holds. Most designs answer it only indirectly: every interaction is stored, and the present is reconstructed at query time by retrieving and reconciling records, so stale values re-enter and the same conflicts are re-litigated. Committing the current value at write time avoids this, but existing write-time (CRUD) memories overwrite, so a wrong update is unrecoverable and prior state is lost. We take the missing combination---commit on arrival while retaining what is displaced---and formalize it as textscMemory of Memory (MoM): memory tracks not only content but the provenance, status, and history of its own entries. We instantiate MoM as textscProvenant Memory (P-Mem), a typed provenance graph whose active frontier exposes one current value per resolved key while displaced values are retained as provenance; typed operations decide whether a new observation supports, supersedes, contests, rejects, revokes, or resolves an existing value. P-Mem's decisive gain is validity rather than accuracy: its turn-level read matches the strongest retrieval memory in accuracy at ~4× fewer read tokens---a retrieval-granularity effect---while graph-guided turn pruning cuts the knowledge-update stale-answer rate (19.4%rightarrow10.9%); on revision chains it stays at 100% where query-time reading collapses to 25%, and, because displaced values are retained rather than overwritten, it recovers committed errors a CRUD memory cannot (100% vs. 0%).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 24 references that are in the map. First posted on arXiv 7 Sep 2026.

Builds on

21 of 24 references.

References · 21

  1. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  2. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  3. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  4. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  5. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  6. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  7. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 400
  8. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 254
  9. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  10. 2025Memory OS of AI Agentcited by 150
  11. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 142
  12. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memorycited by 136
9 more
  1. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 129
  2. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 101
  3. 2026MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Taskscited by 84
  4. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentscited by 62
  5. 2024On the Structural Memory of LLM Agentscited by 37
  6. 2025Preference-Aware Memory Update for Long-Term LLM Agentscited by 20
  7. 2026Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoningcited by 8
  8. 2026Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memorycited by 5
  9. 2026Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory
  2. 2026Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation
  3. 2026PACMI: Provenance-Aware Cascading Memory Invalidation for Long-Term LLM Agents
  4. 2025Memory in Large Language Models: Mechanisms, Evaluation and Evolution
  5. 2026Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It
  6. 2026MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
  7. 2026Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory
  8. 2026Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents