# MoM: Memory of Memory

arXiv: https://arxiv.org/abs/2609.25054 · HTML: https://mlsanity.com/paper/2609.25054/

## 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 (most cited first, 21 of 21)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory](https://mlsanity.com/paper/2511.20857/) (2025)
- [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks](https://mlsanity.com/paper/2602.16313/) (2026)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [On the Structural Memory of LLM Agents](https://mlsanity.com/paper/2412.15266/) (2024)
- [Preference-Aware Memory Update for Long-Term LLM Agents](https://mlsanity.com/paper/2510.09720/) (2025)
- [Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning](https://mlsanity.com/paper/2602.18493/) (2026)
- [Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory](https://mlsanity.com/paper/2603.02473/) (2026)
- [Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMs](https://mlsanity.com/paper/2602.13967/) (2026)

## 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%).