Memory-Augmented Language Models

Ask about this topic

Overview

Memory-augmented language models study how systems can store information from documents, conversations, or earlier tasks and use it in later responses. Approaches include retrieval-augmented generation and structured episodic stores, reusable key-value caches and latent or parametric adapters, and recurrent or fast-weight memories; many add selective writing, compression, routing, or forgetting. Work tests these methods on long-context question answering and recall, reasoning, and continual personalization, using benchmarks such as LoCoMo, LongMemEval, and RULER. Memory can improve access to distant or newly learned information, but systems still struggle with noisy or changing memories, interference with existing capabilities, and evaluations that distinguish successful storage from useful and reliable retrieval.

Latest papers

CardsList

292 papers55 papers in the last four weeks, up 90% on the four weeks before. 0.3% of all new papers.

Apr 19, 2026

AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models

While large language models have achieved remarkable performance in complex tasks, they still need a memory system to utilize historical experience in long-term interactions. Existing memory methods (e.g., A-Mem, Mem0) place excessive emphasis on organizing interactions by frequently rewriting them, however, this heavy reliance on summarization risks diluting essential contextual nuances and obscuring key retrieval features. To bridge this gap, we introduce AnchorMem, a novel memory framework inspired by the Proust Phenomenon in cognitive science, where a specific anchor triggers a holistic recollection. We propose a method that decouples the retrieval unit from the generation context. AnchorMem extracts atomic facts from interaction history to serve as retrieval anchors, while preserving the original context as the immutable context. To reveal implicit narrative cues, we construct an associative event graph that uses higher-order event links that bind sets of related facts into shared event representations, strengthening cross-memory integration without relying on generic entities as bridges. During retrieval, the system anchors queries to specific facts and events to locate relevant memories, but reconstructs the context using the associated raw chunks and events. Our method reconciles fine-grained retrieval with the contextual integrity of interactions. Experiments across three closed-source and open-source models on the LoCoMo benchmark demonstrate that AnchorMem significantly outperforms baselines. Code is available at https://github.com/RayNeo-AI-2025/AnchorMem.

Zhanyu Shen, Sijie Cheng, Zhicheng Guo +3

College of Computer Science and Software Engineering, Shenzhen University · Tsinghua University

Memory-Augmented Language ModelsMemorization in Language ModelsPersistent Memory for Language ModelsMemorization in Generative ModelsLong-Term Conversational Memory
AskPDF
Apr 19, 2026

The Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forward

The most important architectural problem in AI is not the size of the model but the absence of a layer that carries forward what the model has come to understand. Sessions end. Context windows fill. Memory APIs return flat facts that the model has to reinterpret from scratch on every read. The result is intelligence that is powerful per session and amnesiac across time. This position paper argues that the layer which fixes this, the continuity layer, is the most consequential piece of infrastructure the field has not yet built, and that the engineering work to build it has begun in public. The formal evaluation framework for the property described here is the ATANT benchmark (arXiv:2604.06710), published separately with evaluation results on a 250-story corpus; a companion paper (arXiv:2604.10981) positions this framework against existing memory, long-context, and agentic-memory benchmarks. The paper defines continuity as a system property with seven required characteristics, distinct from memory and from retrieval; describes a storage primitive (Decomposed Trace Convergence Memory) whose write-time decomposition and read-time reconstruction produce that property; maps the engineering architecture to the theological pattern of kenosis and the symbolic pattern of Alpha and Omega, and argues this mapping is structural rather than metaphorical; proposes a four-layer development arc from external SDK to hardware node to long-horizon human infrastructure; examines why the physics limits now constraining the model layer make the continuity layer newly consequential; and argues that the governance architecture (privacy implemented as physics rather than policy, founder-controlled class shares on non-negotiable architectural commitments) is inseparable from the product itself.

Samuel Sameer Tanguturi

Kenotic Labs

Memory-Augmented Language ModelsPersistent Memory for Language ModelsLLM MemoryLong-Term Conversational Memory
AskPDF
Apr 18, 2026

LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations

Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered Archival aNd Temporal Episodic Retrieval Network), a lightweight memory layer that proactively archives every conversation turn and restores relevant details after compaction via hybrid retrieval -- requiring zero LLM calls and adding fewer than 25ms of latency per turn. On 94 real multi-turn conversations (1,894 ground-truth facts, human-validated at kappa=0.81), LANTERN-Rerank recovers 78.3% of verifiable facts lost to compaction, significantly outperforming a faithful reimplementation of MemGPT's LLM-driven extraction and multi-query search pipeline (72.4%; Wilcoxon p<0.0001, 95% CI [+3.1, +8.6] pp, d=0.43) at a fraction of the inference cost. Even without the reranker, base LANTERN matches or exceeds this LLM-driven baseline (p=0.005) using zero LLM calls. When four production LLMs answer fact-bearing questions using LANTERN-restored context, accuracy improves by 8.4 percentage points on average (Wilcoxon p<0.05 for each model individually), demonstrating that the recovered context is useful across diverse model architectures. We release the full evaluation framework -- paired significance tests, failure analysis, fact-type stratification, and compaction robustness analysis -- to support reproducibility and future work.

Rahul Subramani

Cisco Systems, Inc.

Memory-Augmented Language ModelsPersistent Memory for Language ModelsLong-Term Conversational MemoryLLM Context Management
AskPDF
Apr 17, 2026

Generic Triple-Latent Compression with Gated Associative Retrieval

We study generic triple-latent sequence models that maintain a running token state and compressed pair-memory pathway to capture higher-order token interactions without benchmark-specific parsing. The triple-latent family improves a small Transformer baseline on byte-level WikiText-2 and on a tokenizer-based MiniMind language-model benchmark, while a recall-focused gated key-value retrieval extension improves associative recall but remains seed-sensitive and much slower in the current reference implementation.

Liu Xiao

Memory-Augmented Language ModelsAutoregressive Language ModelingAssociative MemorySequence Modeling
AskPDF
Apr 15, 2026

Response-Aware User Memory Selection for LLM Personalization

A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model's generation. Existing methods select these subsets primarily using similarity between user memory items and input queries, ignoring how features actually affect the model's response distribution. We propose Response-Utility optimization for Memory Selection (RUMS), a novel method that selects user memory items by measuring the mutual information between a subset of memory and the model's outputs, identifying items that reduce response uncertainty and sharpen predictions beyond semantic similarity. We demonstrate that this information-theoretic foundation enables more principled user memory selection that aligns more closely with human selection compared to state-of-the-art methods, and models 400×400\times larger. Additionally, we show that memory items selected using RUMS result in better response quality compared to existing approaches, while having up to 95%95\% reduction in computational cost.

Jillian Fisher, Jennifer Neville, Chan Young Park

Department of Computer Science and Engineering, University of Washington, Seattle, WA, United States of America · Microsoft Research, Redmond, WA, United States of America

LLM PersonalizationMemory-Augmented Language Models
AskPDF
Apr 9, 2026

MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought

Large Language Models (LLMs) still suffer from severe hallucinations and catastrophic forgetting during causal reasoning over massive, fragmented long contexts. Existing memory mechanisms typically treat retrieval as a static, single-step passive matching process, leading to severe semantic dilution and contextual fragmentation. To overcome these fundamental bottlenecks, we propose MemCoT, a test-time memory scaling framework that redefines the reasoning process by transforming long-context reasoning into an iterative, stateful information search. MemCoT introduces a multi-view long-term memory perception module that enables Zoom-In evidence localization and Zoom-Out contextual expansion, allowing the model to first identify where relevant evidence resides and then reconstruct the surrounding causal structure necessary for reasoning. In addition, MemCoT employs a task-conditioned dual short-term memory system composed of semantic state memory and episodic trajectory memory. This short-term memory records historical search decisions and dynamically guides query decomposition and pruning across iterations. Empirical evaluations demonstrate that MemCoT establishes a state-of-the-art performance. Empowered by MemCoT, several open- and closed-source models achieve SOTA performance on the LoCoMo benchmark and LongMemEval-S benchmark.

Haodong Lei, Junming Liu, Yirong Chen +2

Southeast University Nanjing, Jiangsu, China · Shanghai Artificial Intelligence Laboratory Shanghai, China

Long-Context Reasoning in Language ModelsMemory-Augmented Language ModelsTest-Time ScalingCausal Reasoning in Language Models
AskPDF
Apr 9, 2026

TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation

Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences. However, they still struggle with long-horizon tasks, such as tracking a user's extensive history of conversations or activities. Existing memory mechanisms often fail to capture evolving behaviors, and RAG paradigms are trapped by a quality-efficiency tradeoff. Meanwhile, parametric adaptation is bottlenecked by train-inference gap due to the scarcity of labeled data. To enhance the long-horizon capabilities of PLLMs, we introduce TSUBASA, a two-pronged approach designed to improve memory writing via dynamic memory evolution, and memory reading via self-learning with a context distillation objective to internalize user experiences. Extensive evaluations on long-horizon benchmarks using the Qwen-3 model family (4B to 32B) validate the effectiveness of TSUBASA, surpassing competitive memory-augmented systems that rely primarily on memory writing, such as Mem0 and Memory-R1. Our analyses further confirms that TSUBASA breaks the quality-efficiency barrier to achieve Pareto improvements, delivering robust, high-fidelity personalization with a reduced token budget.

Xinliang Frederick Zhang, Lu Wang

Computer Science and Engineering, University of Michigan, Ann Arbor, MI

Personalized Language ModelsMemory-Augmented Language ModelsPersistent Memory for Language ModelsContext Distillation
AskPDF
Apr 8, 2026

Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction

Large language models (LLMs) hold significant promise for healthcare, yet their reliability in high-stakes clinical settings is often compromised by hallucinations and a lack of granular medical context. While Retrieval Augmented Generation (RAG) can mitigate these issues, standard supervised pipelines require computationally intensive searches over massive external knowledge bases, leading to high latency that is impractical for time-sensitive care. To address this, we introduce Keys to Knowledge (K2K), a novel framework that replaces external retrieval with internal, key-based knowledge access. By encoding essential clinical information directly into the model's parameter space, K2K enables rapid retrieval from internal key-value memory without inference-time overhead. We further enhance retrieval quality through activation-guided probe construction and cross-attention reranking. Experimental results demonstrate that K2K achieves state-of-the-art performance across four benchmark healthcare outcome prediction datasets.

Mingchen Li, Jiatan Huang, Zonghai Yao +1

University of Massachusetts, Amherst · University of Connecticut · University of Massachusetts, Lowell +1

Memory-Augmented Language ModelsMedical LLMsClinical Outcome PredictionLLM Inference Acceleration
AskPDF
Apr 6, 2026

Improving Sparse Memory Finetuning

Large Language Models (LLMs) are typically static after training, yet real-world applications require continual adaptation to new knowledge without degrading existing capabilities. Standard approaches to updating models, like full finetuning or parameter-efficient methods (e.g., LoRA), face a fundamental trade-off: catastrophic forgetting. They modify shared dense representations, causing interference across tasks. Sparse Memory Finetuning (SMF) offers a promising alternative by localizing updates to a small subset of parameters in explicit memory layers. In this work, we present an open-source pipeline to retrofit existing pretrained models (Qwen-2.5-0.5B) with sparse memory modules, enabling effective continual learning on consumer hardware. We extend prior work by introducing a theoretically grounded slot-selection mechanism based on Kullback-Leibler (KL) divergence, which prioritizes memory updates for informationally "surprising" tokens relative to a background distribution. Our experiments demonstrate that our retrofitted models can acquire new factual knowledge with minimal forgetting of held-out capabilities, validating the sparse update hypothesis in a practical setting.

Satyam Goyal, Anirudh Kanchi, Garv Shah +1

University of Michigan, Ann Arbor

Continual Learning for LLMsSparse Fine-TuningMemory-Augmented Language ModelsParameter-Efficient Fine-TuningCatastrophic Forgetting
AskPDF
Apr 6, 2026

Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space

Experiments probing natural language processing by both humans and LLMs suggest that the meaning of a semantic expression is indeterminate prior to the act of interpretation rather than being specifiable simply as the sum of its parts (i.e. compositionality). This observer-dependent act dynamically actualizes meaning under genuine contextuality more consistent with quantum logical mechanisms than with classical Boolean approaches that assume separability, motivating an approach to language modeling that utilizes a Hilbert space formalism. In this work, we introduce Phase-Associative Memory (PAM) -- a complex-valued sequence model whose state S_t \in \mathbb{C}^{d \times d} accumulates outer products of complex token embeddings retrieved through the conjugate inner product Re⟨K∣Q⟩/d\mathrm{Re}\langle K \mid Q\rangle / \sqrt{d} -- and evaluate it against a structurally matched real-valued ablation. Both architectures train stably across a 5M--100M parameter sweep on WikiText-103 under identical conditions; PAM sits at higher absolute loss at every measured scale but improves more rapidly with parameter count, with power-law exponents of −0.15-0.15 vs.\ −0.12-0.12 in loss and −0.65-0.65 vs.\ −0.49-0.49 in perplexity that narrow the gap between the two architectures monotonically. Further investigation of complex-valued sequence modeling at larger scales could reveal that the loss plateau characteristic of real-valued state-of-the-art language models (e.g. transformers) is reachable with PAM-style architectures with an order of magnitude fewer parameters than the current frontier (∼\sim1T), implying that similar capabilities are achievable at sizes runnable on consumer-grade hardware.

Gowrav Vishwakarma, Christopher J. Agostino

Xavoc Technocrats Pvt. Ltd., https: // xavoc. com , India · NPC Worldwide, Bloomington, Indiana 47403, USA

Autoregressive Language ModelingComplex-Valued Neural NetworksAssociative MemoryQuantum-Inspired MLMemory-Augmented Language Models
AskPDF
Apr 1, 2026

Procedural Knowledge at Scale Improves Reasoning

Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat each problem in isolation and do not systematically reuse knowledge from prior reasoning trajectories. In particular, they underutilize procedural knowledge: how to reframe a problem, choose an approach, and verify or backtrack when needed. We introduce Reasoning Memory, a retrieval-augmented generation (RAG) framework for reasoning models that explicitly retrieves and reuses procedural knowledge at scale. Starting from existing corpora of step-by-step reasoning trajectories, we decompose each trajectory into self-contained subquestion-subroutine pairs, yielding a datastore of 32 million compact procedural knowledge entries. At inference time, a lightweight in-thought prompt lets the model verbalize the core subquestion, retrieve relevant subroutines within its reasoning trace, and reason under diverse retrieved subroutines as implicit procedural priors. Across six math, science, and coding benchmarks, Reasoning Memory consistently outperforms RAG with document, trajectory, and template knowledge, as well as a compute-matched test-time scaling baseline. With a higher inference budget, averaged across models and tasks, it improves over no retrieval by 19.5% and over the compute-matched baseline by 8.9%. Ablation studies show that these gains come from two key factors: the broad procedural coverage of the source trajectories and our decomposition and retrieval design, which together enable effective extraction and reuse of procedural knowledge. Our experiment code is available at https://github.com/facebookresearch/reasoning-memory.

Di Wu, Devendra Singh Sachan, Wen-tau Yih +1

University of California, Los Angeles · Meta FAIR

Retrieval-Augmented ReasoningLLM ReasoningKnowledge Augmentation for Language ModelsStructured Reasoning in Language ModelsMemory-Augmented Language Models
AskPDF
Mar 30, 2026

Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction

Large language models lack persistent, structured memory for long-term interaction and context-sensitive retrieval. Expanding context windows does not solve this: recent evidence shows that context length alone degrades reasoning by up to 85% - even with perfect retrieval. We propose a bio-inspired memory framework grounded in complementary learning systems theory, cognitive behavioral therapy's belief hierarchy, dual-process cognition, and fuzzy-trace theory, organized around three principles: (1) Memory has valence, not just content - pre-computed emotional-associative summaries (valence vectors) organized in an emergent belief hierarchy inspired by Beck's cognitive model enable instant orientation before deliberation; (2) Retrieval defaults to System 1 with System 2 escalation - automatic spreading activation and passive priming as default, with deliberate retrieval only when needed, and graded epistemic states that address hallucination structurally; and (3) Encoding is active, present, and feedback-dependent - a thalamic gateway tags and routes information between stores, while the executive forms gists through curiosity-driven investigation, not passive exposure. Seven functional properties specify what any implementation must satisfy. Over time, the system converges toward System 1 processing - the computational analog of clinical expertise - producing interactions that become cheaper, not more expensive, with experience.

Diego C. Lerma-Torres

Universidad de Guanajuato

Persistent Memory for Language ModelsLong-Term Conversational MemoryMemory-Augmented Language ModelsContinual LearningAssociative Memory
AskPDF
Mar 29, 2026

The Root Theorem of Context Engineering

Every system that maintains a large language model conversation beyond a single session faces two inescapable constraints: the context window is finite, and information quality degrades with accumulated volume. We formalize these constraints as axioms and derive a single governing principle -- the Root Theorem of Context Engineering: maximize signal-to-token ratio within bounded, lossy channels. From this principle, we derive five consequences without additional assumptions: (1)~a quality function F(P)F(P) that degrades monotonically with injected token volume, independent of window size; (2)~the independence of signal and token count as optimization variables; (3)~a necessary gate mechanism triggered by fidelity thresholds, not capacity limits; (4)~the inevitability of homeostatic persistence -- accumulate, compress, rewrite, shed -- as the only architecture that sustains understanding indefinitely; and (5)~the self-referential property that the compression mechanism operates inside the channel it compresses, requiring an external verification gate. We show that append-only systems necessarily exceed their effective window in finite time, that retrieval-augmented generation solves search but not continuity, and that the theorem's constraint structure converges with biological memory architecture through independent derivation from shared principles. Engineering proof is provided through a 60+-session persistent architecture demonstrating stable memory footprint under continuous operation -- the divergence prediction made concrete. The Root Theorem establishes context engineering as an information-theoretic discipline with formal foundations, distinct from prompt engineering in both scope and method. Shannon solved point-to-point transmission. Context engineering solves continuity.

Borja Odriozola Schick

Independent Researcher

Context EngineeringLLM Context ManagementPersistent Memory for Language ModelsMemory-Augmented Language Models
AskPDF
Mar 28, 2026

Beyond Acoustic Prefixes: Persistent Access to Serialized Acoustic Memory for LLM-Based Multi-Talker Speech Recognition

Large language models (LLMs) provide strong linguistic priors for serialized output training (SOT), yet LLM-based multi-talker ASR degrades substantially as the number of overlapping talkers increases. Conventional systems expose acoustic evidence primarily through an initial projected mixture prefix, requiring the decoder to preserve and recover talker-relevant information indirectly throughout autoregressive generation. We first examine whether this limitation can be resolved by enriching the static prefix using discrete connectionist temporal classification (CTC) tokens, hybrid token--acoustic prompts, and continuous talker-specific representations. The results suggest that acoustic content alone does not fully address the conditioning bottleneck. We therefore extend onset-based serialization from the output target to the acoustic-conditioning pathway and introduce persistent decoder-side access to SOT-aligned serialized acoustic memory. Talker-specific representations are organized in utterance-onset order and retained as external acoustic memory, while the conventional mixture prefix provides a complementary global-conditioning path. LLM layers query this memory throughout generation through gated residual cross-attention. We further introduce a second adaptation stage that jointly applies low-rank updates to the acoustic-retrieval pathway and selected LLM self-attention projections. Experiments on LibriMix show consistent improvements over static-prefix prompting. These results indicate that effective LLM-based multi-talker ASR depends not only on providing richer acoustic representations, but also on maintaining persistent access to acoustic evidence structured according to the serialized output.

Hao Shi, Yuan Gao, Xugang Lu +1

Graduate School of Informatics, Kyoto University, Kyoto, Japan · National Institute of Information and Communications Technology, Japan

Multi-Speaker ASRMemory-Augmented Language ModelsAutomatic Speech RecognitionSpeech Language Models
AskPDF
Mar 27, 2026

MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference

Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-duplicate queries across users and sessions. In this work, we propose MemBoost, a memory-boosted LLM serving framework that enables a lightweight model to reuse previously generated answers and retrieve relevant supporting information for cheap inference, while selectively escalating difficult or uncertain queries to a stronger model. Unlike standard retrieval-augmented generation, which primarily grounds a single response, MemBoost is designed for interactive settings by supporting answer reuse, continual memory growth, and cost-aware routing. Experiments across multiple models under simulated workloads show that MemBoost substantially reduces expensive large-model invocations and overall inference cost, while maintaining high answer quality comparable to the strong model baseline.

Joris Köster, Zixuan Liu, Siavash Khajavi +1

Department of Computer Science, Aalto University, Finland · Department of Computer Science, Tulane University, LA, USA · Department of Industrial Engineering and Management, Aalto University, Finland

LLM Inference ServingCost-Aware InferenceLLM RoutingMemory-Augmented Language Models
AskPDF
Mar 25, 2026

Enhanced Mycelium of Thought (EMoT): A Bio-Inspired Hierarchical Reasoning Architecture with Strategic Dormancy and Mnemonic Encoding

Current prompting paradigms for large language models (LLMs), including Chain-of-Thought (CoT) and Tree-of-Thoughts (ToT), follow linear or tree-structured reasoning paths that lack persistent memory, strategic dormancy, and cross-domain synthesis. We present the Enhanced Mycelium of Thought (EMoT) framework, a bio-inspired reasoning architecture that organises cognitive processing into a four-level hierarchy (Micro, Meso, Macro, Meta), implements strategic dormancy and reactivation of reasoning nodes, and integrates a Memory Palace with five mnemonic encoding styles. EMoT is a research prototype for complex, multi-domain problems, not a general-purpose prompting enhancement. Two complementary evaluations reveal a characteristic trade-off. In a blind LLM-as-Judge evaluation across three domains, EMoT achieved near-parity with CoT (4.20 vs. 4.33/5.0) with higher stability, and outperformed CoT on Cross-Domain Synthesis (4.8 vs. 4.4). Ablation studies show that strategic dormancy is architecturally essential (quality collapsed from 4.2 to 1.0 when disabled). On a 15-item short-answer benchmark, EMoT (27%) substantially underperformed simpler baselines, confirming systematic overthinking on simple problems. These results are subject to important limitations: small sample sizes (n=3 complex cases, n=15 short-answer items), LLM-as-Judge evaluation with potential self-preference bias, and approximately 33-fold computational cost overhead. To our knowledge, EMoT is the first reasoning framework to combine hierarchical topology, strategic thought dormancy with reactivation, and mnemonic memory encoding in a single architecture.

Florian Odi Stummer

Institute of General Medicine Martin Luther University Halle-Wittenberg, Germany

LLM PromptingMemory-Augmented Language ModelsOverthinking in Language Models
AskPDF
Mar 23, 2026

TAMTRL: Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning in Long-Context Compression

The rapid progress of large language models (LLMs) has led to remarkable performance gains across a wide range of tasks. However, when handling long documents that exceed the model's context window limit, the entire context cannot be processed in a single pass, making chunk-wise processing necessary. This requires multiple turns to read different chunks and update memory. However, supervision is typically provided only by the final outcome, which makes it difficult to evaluate the quality of memory updates at each turn in the multi-turn training setting. This introduces a temporal credit assignment challenge. Existing approaches, such as LLM-as-a-judge or process reward models, incur substantial computational overhead and suffer from estimation noise. To better address the credit assignment problem in multi-turn memory training, we propose Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning (TAMTRL). TAMTRL leverages relevant documents as teacher signals by aligning them with each turn of model input and assigns rewards through normalized probabilities in a self-supervised manner. This provides fine-grained learning signals for each memory update and improves long-context processing. Experiments with multiple models of varying scales across seven long-context benchmarks show that TAMTRL consistently outperforms strong baselines, demonstrating its effectiveness. Our code is available at https://anonymous.4open.science/r/TAMTRL-F1F8.

Li Wang, Yandong Wang, Xin Yu +3

School of Artificial Intelligence, Beihang University, Beijing, 100191, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China · Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, China

RL for Language ModelsLong-Context Language ModelingReward ShapingMemory-Augmented Language Models
AskPDF
Mar 23, 2026

HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization

Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce personalized text. While lightweight large language models (LLMs) make on-device auxiliary generation feasible, enabling deeply personalized, privacy-preserving, and real-time generative IMEs poses fundamental challenges.To this end, we present HUOZIIME, a personalized on-device IME powered by LLM. We endow HUOZIIME with initial human-like prediction ability by post-training a base LLM on synthesized personalization data. Notably, a hierarchical memory mechanism is designed to continually capture and leverage user-specific input history. Furthermore, we perform systemic optimizations tailored to on-device LLMbased IME deployment, ensuring efficient and responsive operation under mobile constraints.Experiments demonstrate efficient on-device execution and high-fidelity memory-driven personalization. Code and package are available at https://github.com/Shan-HIT/HuoziIME.

Baocai Shan, Yuzhuang Xu, Wanxiang Che

Harbin Institute of Technology, Harbin, China

Personalized Language ModelsOn-Device Language Model InferenceMemory-Augmented Language Models
AskPDF
Mar 23, 2026

Generalizable Self-Evolving Memory for Automatic Prompt Optimization

Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits generalization across heterogeneous queries and prevents models from accumulating reusable prompting knowledge over time. In this paper, we propose MemAPO, a memory-driven framework that reconceptualizes prompt optimization as generalizable and self-evolving experience accumulation. MemAPO maintains a dual-memory mechanism that distills successful reasoning trajectories into reusable strategy templates while organizing incorrect generations into structured error patterns that capture recurrent failure modes. Given a new prompt, the framework retrieves both relevant strategies and failure patterns to compose prompts that promote effective reasoning while discouraging known mistakes. Through iterative self-reflection and memory editing, MemAPO continuously updates its memory, enabling prompt optimization to improve over time rather than restarting from scratch for each task. Experiments on diverse benchmarks show that MemAPO consistently outperforms representative prompt optimization baselines while substantially reducing optimization cost.

Guanbao Liang, Yuanchen Bei, Sheng Zhou +5

Zhejiang University · University of Illinois Urbana-Champaign · Alibaba Group

Automatic Prompt OptimizationLanguage Model Self-ImprovementMemory-Augmented Language Models
AskPDF
Mar 22, 2026

Mixture of Chapters: Scaling Learnt Memory in Transformers

Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tokens, randomly initialized and trained end-to-end, that transformer layers query via cross-attention to retrieve stored knowledge. To scale memory capacity without prohibitive attention costs, we propose chapter-based routing inspired by Mixture-of-Experts architectures, partitioning the memory bank into chapters and training a router to select relevant subsets per input. This enables scaling to 262K memory tokens while maintaining tractable computation. We evaluate our approach against standard transformers (in iso-FLOP settings) on pre-training and instruction fine-tuning across relevant benchmarks. Our models surpass iso-FLOP baselines suggesting scope for a new axis of scaling, demonstrating that explicit associative memory provides complementary capacity to what is captured implicitly in model parameters. Additionally, we observe improved knowledge retention under continued training, with robustness to forgetting when transitioning between training phases (e.g., pretraining to instruction fine-tuning).

Tasmay Pankaj Tibrewal, Pritish Saha, Ankit Meda +2

IIT Kharagpur · Fractal AI

Memory-Augmented Language ModelsPersistent Memory for Language ModelsAssociative Memory
AskPDF
Mar 21, 2026

MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning

As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as Multi-Query Attention (MQA) and Multi-Latent Attention (MLA) reduce memory by sharing or compressing KV features, they often trade off representation quality or incur runtime overhead. We propose Memory-Keyed Attention (MKA), a hierarchical attention mechanism that integrates multi-level KV caches (local, session, and long-term) and learns to route attention across them dynamically. We further introduce Route-Fused MKA (FastMKA), a broadcast-routed variant that fuses memory sources before attention computation for improved efficiency. Experiments on different sequence lengths show that FastMKA achieves a favorable accuracy-efficiency trade-off: comparable perplexity to MLA while achieving up to 5x faster training throughput and 1.8x lower evaluation latency. These results highlight MKA as a practical and extensible framework for efficient long-context attention.

Dong Liu, Yanxuan Yu, Ben Lengerich +1

University of California, Los Angeles, Los Angeles, California, USA · Columbia University, New York, New York, USA · University of Wisconsin-Madison, Madison, Wisconsin, USA

Attention MechanismsMemory-Efficient AttentionLong-Context Language ModelingKV-Cache ManagementLLM Inference AccelerationMemory-Augmented Language Models
AskPDF
Mar 20, 2026

A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy: iterative verification-rectification is computationally expensive and prone to being trapped in faulty reasoning, while best-of-N selection requires extensive sampling without addressing internal model flaws. We propose a training-free regeneration paradigm that leverages an offline-curated contrastive Reflection Memory (RM) to provide corrective guidance, while regenerating from scratch helps break out of faulty reasoning. At inference time, the method performs RM-guided self-verification followed by a single RM-guided regeneration, avoiding both iterative correction and multi-sample selection. We evaluated our method on nine benchmarks that span algorithmic, reasoning, symbolic, and domain-specific tasks in both small- and large-scale LLMs. Experiment results show that our method outperforms prior methods while maintaining low computational cost.

Yuran Li, Di Wu, Benoit Boulet

Department of Electrical and Computer Engineering, McGill University · Department of Mechanical, Industrial and Aerospace Engineering, Concordia University

Language Model Self-VerificationLanguage Model Self-ImprovementLLM Self-CorrectionMemory-Augmented Language Models
AskPDF
Mar 20, 2026

Trained Persistent Memory for Frozen Decoder-Only LLMs

Decoder-only language models are stateless: hidden representations are discarded after every forward pass and nothing persists across sessions. Jeong (2026a) showed that trained memory adapters give a frozen encoder-decoder backbone persistent latent-space memory, building on the lateral-memory framework of Jeong (2026b,c). Here we ask whether the same principle transfers to the decoder-only setting, where no cross-attention pathway exists and memory must enter through self-attention alone. We adapt six methods -- prefix, parallel cross-attention, KV extension, Hebbian memory, context-gated branch, and slot-based sparse write -- to a frozen GPT-2, training only a small adapter θmemθ_{mem}. The write rule is shared; only the read injection changes from decoder cross-attention to self-attention KV prefix or parallel branch. On LoCoMo we find a striking inductive-bias dichotomy: at 1×1\times capacity, three methods with strong architectural priors -- cross-attention (M.2), Hebbian (M.4), and slot write (M.6) -- achieve retained-memory scores of 7−18%7-18\% and knowledge gains ΔKΔK of 7−107-10, while the other three fail (<0.4%< 0.4\%). At 10×10\times capacity all six converge, showing the gap is architectural, not fundamental. Together with the encoder-decoder results of Jeong (2026a) and the brain-inspired modules of Jeong (2026b,c), these findings establish persistent latent-space memory as a general paradigm spanning major transformer families.

Hong Jeong

Inha University in Tashkent, Uzbekistan

Persistent Memory for Language ModelsMemory-Augmented Language ModelsLLM MemoryDecoder-Only Language Models
AskPDF
Mar 17, 2026

Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods

Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a proof-of-concept pilot study showing that persistent memory in the continuous latent space of a frozen LLM is feasible -- even under severe resource constraints (a single frozen Flan-T5-XL backbone, small trainable adapters, a single dataset). We implement six architectural methods spanning three injection points and four write mechanisms; unlike text-level memory systems, every write and read is a differentiable operation on dense vectors. After training only the adapter, the memory bank continues to accumulate at inference time without gradients, enabling conversational learning. Under a forgetting-curve evaluation on LoCoMo at two capacity scales (1×\times and 10×\times), the stateless baseline scores exactly zero; at 10×\times all six trained adapters produce positive memory-recall curves; at 1×\times three methods collapse, revealing capacity as a critical design parameter. Because the memory bank is a compact numerical array, it can be scaled to arbitrarily large capacity without altering the backbone. We argue that full end-to-end training with larger models, larger data, and orders-of-magnitude larger memory will yield substantially stronger results; this pilot study establishes the feasibility baseline and design-space taxonomy that such efforts require.

Hong Jeong

Inha University in Tashkent, Uzbekistan

Persistent Memory for Language ModelsMemory-Augmented Language ModelsContinual Learning for LLMs
AskPDF
Mar 16, 2026

Selective Memory for Artificial Intelligence: Write-Time Gating with Hierarchical Archiving

Retrieval-augmented generation stores all content indiscriminately, degrading accuracy as noise accumulates. Parametric approaches compress knowledge into weights, precluding selective updates. Neither mirrors biological memory, which gates encoding based on salience and archives rather than deletes superseded information. We introduce write-time gating that filters incoming knowledge objects using composite salience scores (source reputation, novelty, reliability) while maintaining version chains that preserve prior states. Using real LLM evaluation without oracle access to quality labels, write gating achieves 100 percent accuracy versus 13 percent for ungated stores. The critical finding emerges under distractor scaling: at 8:1 distractor ratios, read-time filtering (Self-RAG) collapses to 0 percent while write gating maintains 100 percent, revealing a structural advantage of write-time over read-time curation. Validation on Wikipedia (20 entities), procedurally generated pharmacology data, and 2026 arXiv papers confirms these findings. The gating advantage scales inversely with parametric memory support: +25pp for Wikipedia, +48pp for post-cutoff arXiv, +65pp for procedural data with zero training knowledge. Signal ablation confirms the method does not depend on oracle-correlated metadata. Write gating matches Self-RAG accuracy at one-ninth the query-time cost.

Oliver Zahn, Simran Chana

Independent Researcher · University of Cambridge

Memory-Augmented Language ModelsPersistent Memory for Language ModelsRAG RobustnessRAG Evaluation
AskPDF
Mar 16, 2026

Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on jailbreak defenses that detect and refuse explicitly unsafe inputs, such approaches often overlook contextual safety, which requires models to distinguish subtle contextual differences between scenarios that may appear similar but diverge significantly in safety intent. In this work, we present MM-SafetyBench++, a carefully curated benchmark designed for contextual safety evaluation. Specifically, for each unsafe image-text pair, we construct a corresponding safe counterpart through minimal modifications that flip the user intent while preserving the underlying contextual meaning, enabling controlled evaluation of whether models can adapt their safety behaviors based on contextual understanding. Further, we introduce EchoSafe, a training-free framework that maintains a self-reflective memory bank to accumulate and retrieve safety insights from prior interactions. By integrating relevant past experiences into current prompts, EchoSafe enables context-aware reasoning and continual evolution of safety behavior during inference. Extensive experiments on various multi-modal safety benchmarks demonstrate that EchoSafe consistently achieves superior performance, establishing a strong baseline for advancing contextual safety in MLLMs. All benchmark data and code are available at https://echosafe-mllm.github.io.

Ce Zhang, Jinxi He, Junyi He +2

Robotics Institute, Carnegie Mellon University

Multimodal Large Language ModelsLanguage Model Safety EvaluationLLM Safety EvaluationLLM Safety BenchmarksMemory-Augmented Language Models
AskPDF
Mar 15, 2026

Learning to Forget: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in Large Language Models

Large language models (LLMs) suffer from proactive interference (PI): outdated information in the context window disrupts retrieval of current values. This interference degrades retrieval accuracy log-linearly as stale associations accumulate, a bottleneck that persists regardless of context length and resists prompt-engineering mitigations. Biological brains resolve an analogous challenge through sleep-dependent memory consolidation: synaptic downscaling, selective replay, and targeted forgetting. We propose SleepGate, a biologically inspired framework that augments transformer-based LLMs with a learned sleep cycle over the key-value (KV) cache. SleepGate introduces three mechanisms: (1) a conflict-aware temporal tagger detecting when new entries supersede old ones; (2) a lightweight forgetting gate trained to selectively evict or compress stale cache entries; and (3) a consolidation module that merges surviving entries into compact summaries. These components activate periodically during inference in sleep micro-cycles, governed by an adaptive entropy-based trigger. We formalize a dual-phase training objective jointly optimizing language modeling during the wake phase and post-consolidation retrieval during the sleep phase. Theoretical analysis shows SleepGate reduces the interference horizon from O(n) to O(log n). In experiments with a small-scale transformer (4 layers, 793K parameters), SleepGate achieves 99.5% retrieval accuracy at PI depth 5 and 97.0% at depth 10, while all five baselines -- full KV cache, sliding window, H2O, StreamingLLM, and decay-only ablation -- remain below 18%. Our framework offers an architecture-level solution that prompt engineering cannot address.

Ying Xie

Kennesaw State University

KV-Cache ManagementKnowledge Conflicts in Language ModelsMemory-Augmented Language Models
AskPDF
Mar 14, 2026

GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent

Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative is compressive memory: read a context once, store it in a compact state, and answer many queries from that state. We study this in a context removal setting, where the model must generate an answer without access to the original context at inference time. We introduce GradMem, which writes context into memory via per-sample test-time optimization. Given a context, GradMem performs a few steps of gradient descent on a small set of prefix memory tokens while keeping model weights frozen. GradMem explicitly optimizes a model-level self-supervised context reconstruction loss, resulting in a loss-driven write operation with iterative error correction, unlike forward-only methods. On associative key--value retrieval, GradMem outperforms forward-only memory writers with the same memory size, and additional gradient steps scale capacity much more effectively than repeated forward writes. We further show that GradMem transfers beyond synthetic benchmarks: with pretrained language models, it attains competitive results on natural language tasks including bAbI and SQuAD variants, relying only on information encoded in memory.

Yuri Kuratov, Matvey Kairov, Aydar Bulatov +2

AXXX, Cognitive AI Systems Lab, Moscow, Russia · MIRAI, Moscow, Russia · MBZUAI, Abu Dhabi, UAE +1

Memory-Augmented Language ModelsContext CompressionTest-Time Training
AskPDF
Mar 13, 2026

StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context

Large language models (LLMs) and small language models (SLMs) operate under strict context window and key-value (KV) cache constraints, fundamentally limiting their ability to reason coherently over long interaction horizons. Existing approaches -- extended context windows, retrieval-augmented generation, summarization, or static documentation -- treat memory as static storage and fail to preserve decision-relevant state under long-running, multi-session tasks. We introduce StatePlane, a model-agnostic cognitive state plane that governs the formation, evolution, retrieval, and decay of episodic, semantic, and procedural state for AI systems operating under bounded context. Grounded in cognitive psychology and systems design, StatePlane formalizes episodic segmentation, selective encoding via information-theoretic constraints, goal-conditioned retrieval with intent routing, reconstructive state synthesis, and adaptive forgetting. We present a formal state model, KV-aware algorithms, security and governance mechanisms including write-path anti-poisoning, enterprise integration pathways, and an evaluation framework with six domain-specific benchmarks. StatePlane demonstrates that long-horizon intelligence can be achieved without expanding context windows or retraining models.

Sasank Annapureddy, John Mulcahy, Anjaneya Prasad Thamatani

LLM Context ManagementPersistent Memory for Language ModelsLong-Horizon LLM AgentsMemory-Augmented Language ModelsCognitive Architectures for AI Agents
AskPDF
Mar 12, 2026

LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

Most current long-context language models still rely on attention to handle both local interaction and long-range state, which leaves relatively little room to test alternative decompositions of sequence modeling. We propose LPC-SM, a hybrid autoregressive architecture that separates local attention, persistent memory, predictive correction, and run-time control within the same block, and we use Orthogonal Novelty Transport (ONT) to govern slow-memory writes. We evaluate a 158M-parameter model in three stages spanning base language modeling, mathematical continuation, and 4096-token continuation. Removing mHC raises the Stage-A final LM loss from 12.630 to 15.127, while adaptive sparse control improves the Stage-B final LM loss from 12.137 to 10.787 relative to a matched fixed-ratio continuation. The full route remains stable at sequence length 4096, where Stage C ends with final LM loss 11.582 and improves the delayed-identifier diagnostic from 14.396 to 12.031 in key cross-entropy. Taken together, these results show that long-context autoregressive modeling can be organized around a broader division of labor than attention alone.

Keqin Xie

Independent Researcher, Suzhou, China

Long-Context Language ModelingAutoregressive Language ModelingLong-Range Dependency ModelingMemory-Augmented Language ModelsPersistent Memory for Language ModelsPredictive Coding
AskPDF