Pith. sign in

REVIEW 22 cited by

MEMORYLLM: Towards Self-Updatable Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.04624 v2 pith:257IWD2C submitted 2024-02-07 cs.CL

MEMORYLLM: Towards Self-Updatable Large Language Models

classification cs.CL
keywords memoryllmmodelknowledgemodelsbenchmarkseffectivelyevaluationslanguage
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Existing Large Language Models (LLMs) usually remain static after deployment, which might make it hard to inject new knowledge into the model. We aim to build models containing a considerable portion of self-updatable parameters, enabling the model to integrate new knowledge effectively and efficiently. To this end, we introduce MEMORYLLM, a model that comprises a transformer and a fixed-size memory pool within the latent space of the transformer. MEMORYLLM can self-update with text knowledge and memorize the knowledge injected earlier. Our evaluations demonstrate the ability of MEMORYLLM to effectively incorporate new knowledge, as evidenced by its performance on model editing benchmarks. Meanwhile, the model exhibits long-term information retention capacity, which is validated through our custom-designed evaluations and long-context benchmarks. MEMORYLLM also shows operational integrity without any sign of performance degradation even after nearly a million memory updates. Our code and model are open-sourced at https://github.com/wangyu-ustc/MemoryLLM.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 22 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MemTrace: Probing What Final Accuracy Misses in Long-Term Memory

    cs.AI 2026-06 unverdicted novelty 7.0

    MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.

  2. MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning

    cs.CL 2025-11 unverdicted novelty 7.0

    MemSearcher trains LLMs to manage compact memory in multi-turn searches via multi-context GRPO for end-to-end RL, outperforming ReAct-style baselines with stable token counts.

  3. Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

    cs.CL 2025-07 unverdicted novelty 7.0

    MemoryAgentBench is a new multi-turn benchmark assessing four memory competencies in LLM agents—accurate retrieval, test-time learning, long-range understanding, and selective forgetting—showing that existing methods ...

  4. Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory

    cs.CL 2026-07 conditional novelty 6.0

    Long-context memory can be organized by caching intermediate residual states and recomputing only query-conditioned upper layers over a bounded retrieved pack.

  5. What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

    cs.LG 2026-07 conditional novelty 6.0

    KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.

  6. A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory

    cs.AI 2026-07 conditional novelty 6.0

    Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.

  7. Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue

    cs.CL 2026-05 unverdicted novelty 6.0

    RefMem-Bench benchmarks reflective memory in dialogue with 26K instances across eight dimensions, and REMIND improves model accuracy via hierarchical evidence retrieval, grounding, and abstraction.

  8. Rethinking Memory as Continuously Evolving Connectivity

    cs.CL 2026-05 unverdicted novelty 6.0

    FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.

  9. Simulating Human Memory with Language Models

    cs.CL 2026-05 unverdicted novelty 6.0

    Language models show superior memory to humans on psych experiments but can be adjusted via prompting and compaction to forget more human-like, yielding better user simulators.

  10. In-Place Test-Time Training

    cs.LG 2026-04 conditional novelty 6.0

    In-Place TTT adapts LLM MLP projection matrices at test time with a next-token-aligned objective and chunk-wise updates, enabling better long-context performance as a drop-in enhancement.

  11. Position: Modular Memory is the Key to Continual Learning Agents

    cs.LG 2026-03 conditional novelty 6.0

    A modular memory combining in-context learning and in-weight learning is proposed as the key to continual learning agents.

  12. HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling

    cs.AI 2026-02 unverdicted novelty 6.0

    HyMem introduces dual-granular memory storage with a lightweight summary module for fast responses and selective activation of a deep LLM module for complex queries, outperforming full-context baselines by 92.6% lower...

  13. A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory

    cs.AI 2026-07 unverdicted novelty 5.0

    ATMA adds state labels and evidence packets to existing memory systems to reduce ghost memory failures, with reported gains on a new LTP benchmark and LoCoMo.

  14. AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance

    cs.AI 2026-06 unverdicted novelty 5.0

    AgRefactor deploys a self-evolving multi-agent workflow that combines LLM rewrites with automated tools to convert software into HLS code, matching or beating baselines on long benchmarks and delivering 6.51x geometri...

  15. EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents

    cs.CL 2026-06 conditional novelty 5.0

    EMBER learns to retain budgeted, source-backed evidence capsules so long-horizon agents recover answer-relevant facts without rereading the full history.

  16. EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents

    cs.CL 2026-06 unverdicted novelty 5.0

    EMBER learns to retain source-backed evidence capsules under a fixed token budget, improving F1, Retain-Recall, and Read-Recall on LongMemEval-RR over budgeted baselines.

  17. From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs

    cs.IR 2025-04 unverdicted novelty 5.0

    The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.

  18. Memory for Large Language Models

    cs.CL 2026-07 conditional novelty 4.0

    The paper organizes LLM memory architectures along three axes—implicit vs explicit representation, offline vs online update, and short vs long-term persistence—plus finer-grained update rules.

  19. TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

    cs.AI 2026-06 unverdicted novelty 4.0

    TrustMem introduces a verifier for memory update transitions and preference-guided RL to cut omission, corruption, and hallucination rates in LLM agent memory while reaching SOTA on MemoryAgentBench and HaluMem.

  20. MemVerse: Multimodal Memory for Lifelong Learning Agents

    cs.AI 2025-12 reject novelty 4.0

    MemVerse reports large gains on multimodal benchmarks by adding a hierarchical knowledge-graph memory plus fine-tuned parametric recall, but its strongest video-retrieval result uses ground-truth caption-video pairs i...

  21. Token-Operations-Oriented Inference Optimization Techniques for Large Models

    cs.SE 2026-06 conditional novelty 3.0

    A survey of large-model inference optimization, organized as a four-layer 'token-operations' taxonomy: multi-model fusion, model optimization, compute-model fusion, and compute-network-model fusion.

  22. Token-Operations-Oriented Inference Optimization Techniques for Large Models

    cs.SE 2026-06 unverdicted novelty 3.0

    The paper introduces a four-layer technical architecture for token-operations-oriented inference optimization in large models and reviews key technologies and industry status at each layer.