MIGRO: A Decoupled and Portable Long-Term Memory System for Language Models

Mingxi Zou, Yinghui Xu, Jiaxiang Chen, Langzhang Liang, Wei Zhu, Peng Ye, Runkai Zhao, Ruoxi Jiang, Sijin Chen, Song Wang, Zhuo Wang, Lizhen Qu, Zenglin Xu

TL;DR

MIGRO is a decoupled long-term memory system that allows a user's interaction history to persist and grow even as the underlying Large Language Model (LLM) is upgraded or replaced. By separating exact evidence preservation from approximate semantic indexing and using LLM-based lossless compression, MIGRO achieves state-of-the-art performance while using up to 99.3% less private memory than existing baselines.

What Problem Does This Paper Address?

Most current LLM memory systems are "model-bound"—they are tightly coupled to a specific model's vocabulary, tokenization, or internal latent states. This creates a major bottleneck: when you upgrade your model (e.g., from Qwen-4B to Qwen-32B), you typically lose the accumulated user history or must pay a massive computational cost to rebuild the memory from scratch.

Furthermore, many systems summarize information at "write-time." This is problematic because a summary fixed today might discard details that become crucial for a question asked six months from now. The authors argue that memory should outlive the model, treating user experience as a persistent state that can be handed off between successive reasoning engines.

MIGRO decouples memory from the model, allowing history to persist across model upgrades.

Methods

MIGRO introduces a decoupled architecture based on two core principles:

  1. Asymmetric Fidelity with Deferred Selectivity: Instead of summarizing at write-time, MIGRO preserves historical evidence exactly (canonical source-token IDs). It organizes this evidence approximately using a shared semantic index for retrieval. The decision of what is relevant is "deferred" until a specific query is known, ensuring no information is prematurely lost.
  2. Portable Host Interfaces: To handle different models with varying vocabularies and embedding spaces, MIGRO uses host-specific "transport" interfaces. These interfaces map the stored canonical evidence into inputs the current "host" model can understand at read-time.
  3. Reversible Causal Coding: To make long-term storage practical, MIGRO uses a frozen LLM as a probability estimator for arithmetic coding. This allows for lossless, high-density compression of the memory state, making it far more compact than raw text or vector databases.
The MIGRO lifecycle: Writing to a shared state, reading via host-specific adaptation, and persisting through causal compression.

Datasets

The authors evaluated MIGRO across five diverse benchmarks covering different aspects of long-term memory:

  • LoCoMo: Conversational recall and cross-session reasoning.
  • LongMemEval-S: Multi-session QA and temporal understanding.
  • MemOps: Evolving memory operations like updating or forgetting information.
  • MemoryAgentBench: Incremental interaction and handling revised knowledge.
  • BEAM-1M: Long-horizon recall within massive, million-token interaction histories.

Key Insights and Ideas

  • The "Enduring Object": The user's history is the primary asset; the LLM is just a swappable reasoning engine.
  • Fidelity Separation: You don't need high precision for the index (where things are) as long as you have perfect precision for the evidence (what things are). Quantizing the index saves massive space without hurting retrieval quality.
  • LLMs are World-Class Compressors: By using the statistical regularity of language captured by LLMs, MIGRO can store vast histories at a fraction of the usual cost (averaging ~1.8 bytes per token for million-token histories).
  • Continuity of Accumulation: Portability isn't just a one-time transfer; it’s the ability to keep writing to the same inherited state using a new model, maintaining a continuous thread of experience.

Key Results

MIGRO consistently outperformed all seven baselines (including Mem0, TiMem, and LSTMem) across all benchmarks:

  • Efficiency vs. Quality: On the LoCoMo benchmark, MIGRO scored 7.3% higher than the strongest baseline while using 99.3% less private memory.
  • Seamless Handoff: After switching models, MIGRO retained 99.9% of the quality achieved by a model that had seen the full history from the start.
  • Scalable Storage: For million-token histories, MIGRO used 57.5% less storage than the most compact baseline.
  • Joint Frontier: MIGRO achieved 2.60x the answer quality per private MB compared to the best-performing baseline.
Figure 1. MIGRO’s capability profiles across performance, transfer, and storage. Farther out indicates stronger measured capability on each axis. Appendix D.8 defines the axes and their scales.

Limitations and Future Work

While MIGRO excels at fact preservation and retrieval, the authors note that certain complex reasoning tasks remain difficult. Specifically, contradiction resolution and precise event ordering in very long histories (million+ tokens) still pose challenges for current readers.

Future work may involve improving the "discourse links" between records to help models better navigate temporal relationships and conflicting information. Additionally, the current implementation does not yet support crash-consistent transactional updates or incremental neural recoding, which would be necessary for production-grade database integration.

Summary updated

Abstract

Language models evolve, but the observations, revisions, and context accumulated through user interactions should remain usable. Each new model must be able to retrieve past evidence, track revisions, and add new observations. We present MIGRO, a decoupled long-term memory system that treats experience as a persistent state shared across successive language models. MIGRO follows a simple principle: preserve historical evidence exactly, organize it approximately, and decide what to retrieve only when the question is known. We call this asymmetric fidelity with deferred selectivity. A shared semantic index supports retrieval, while exact records retain observations and their historical relationships. Because models differ in vocabulary and tokenization, host-specific interfaces convert selected evidence into inputs the receiving model can use. Reversible encoding reduces archival storage while enabling exact recovery. The shared state and its access interfaces let successive hosts read and extend the accumulated experience. On matched LoCoMo states, MIGRO scores 7.3% higher and uses 99.3% less private memory than the strongest quality baseline. After handoff, continued writing retains 99.9% of full-history rebuilding quality by extending the inherited state. On million-token BEAM histories, MIGRO uses 57.5% less private storage on average than the most compact baseline. MIGRO combines high answer quality, continued memory growth across hosts, and low storage cost. Code is available at https://github.com/zOUMINGXI/MIGRO.
BibTeX
@misc{zou2026migro,
  author = {Mingxi Zou and Yinghui Xu and Jiaxiang Chen and Langzhang Liang and Wei Zhu and Peng Ye and Runkai Zhao and Ruoxi Jiang and Sijin Chen and Song Wang and Zhuo Wang and Lizhen Qu and Zenglin Xu},
  title = {{MIGRO: A Decoupled and Portable Long-Term Memory System for Language Models}},
  year = {2026},
  eprint = {2611.15315},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.15315},
}
Figure