arXivPaperNeeds Review

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability

Agent memory can break across model upgrades even when the store is unchanged. Test migrations by direction, rebuild embeddings completely, and retain raw histories for repair.

arXiv · Sep 4, 2026

Open Source Open Markdown Open JSON

Source Summary

Across **48 synthetic histories**, fixed-schema knowledge graphs barely changed after a writer-model swap, while compressed notes moved by **+9.91 or −13.28 percentage points** depending on migration direction. A half-migrated RAG index gained 4.96 points versus **11.90 points with full re-embedding**.

Practical Implication

Treat model upgrades as memory migrations: test each model direction separately, keep embedding spaces isolated, and re-embed the full index. Prefer normalized schemas where practical, and retain source histories instead of relying only on model-written notes.

Agent-Ready Context

Across **48 synthetic histories**, fixed-schema knowledge graphs barely changed after a writer-model swap, while compressed notes moved by **+9.91 or −13.28 percentage points** depending on migration direction. A half-migrated RAG index gained 4.96 points versus **11.90 points with full re-embedding**.

Treat model upgrades as memory migrations: test each model direction separately, keep embedding spaces isolated, and re-embed the full index. Prefer normalized schemas where practical, and retain source histories instead of relying only on model-written notes.

The evidence covers two open-weight models below 10B parameters and synthetic histories with exact answers. Store-only note repair missed the 90% recovery target in every case; raw history enabled recovery in **34 of 48 cases** for one tested direction, not universally.

Connected Context · Feed7 Judgment

This makes model portability a missing reliability constraint across the prior memory designs. It favors fixed, normalized, inspectable representations over model-authored compression when upgrades are expected, and shows that retrieval continuity requires full embedding migration rather than a mixed index. The limited models and synthetic histories narrow this to a concrete migration warning, not a universal ranking of memory architectures.

thedotmack/claude-memClaude-Mem’s compressed persistent observations create the kind of model-written memory whose portability this study finds direction-dependent, strengthening the case for retaining source history alongside summaries.UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task StreamsUniMem’s learned consolidation raises an additional portability question: recurring knowledge moved into model parameters may be harder to preserve across model replacement than normalized episodic records.Intelligence + Continual Learning = Expertise — Yu Su, NeoCognitionThe continual-learning vision depends on reusable state surviving upgrades; this study supplies a concrete stability requirement and shows that raw histories can sometimes recover knowledge that compressed notes alone cannot.MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based AgentsMemLens treats retention as a quality and cost optimization, while this study adds migration robustness as another criterion for deciding which representations and source records to preserve.

Context Map

agentcodingdata#agent-memory#retrieval#agent-reliability

Uncertainty

The evidence covers two open-weight models below 10B parameters and synthetic histories with exact answers. Store-only note repair missed the 90% recovery target in every case; raw history enabled recovery in **34 of 48 cases** for one tested direction, not universally.