Persistent Memory for Language Models

Ask about this topic

Overview

Persistent memory lets language models carry useful information across conversations, tasks, or long sequences without repeatedly processing the full history. Approaches include extracting and compressing facts or episodes for lexical, vector, and graph-based retrieval; managing memory through updates, provenance, and forgetting; and adding learned latent, parametric, recurrent, or persistent key-value states. Systems are commonly tested on cross-session question answering and personalization benchmarks such as LoCoMo and LongMemEval, as well as long-context reasoning and interactive agent tasks. The central tension is retaining enough faithful, current evidence for reliable reasoning while controlling storage, token, and latency costs—and preventing stale, sensitive, or poisoned memories from shaping answers.

Latest papers

CardsList

272 papers50 papers in the last four weeks, up 67% on the four weeks before. 0.3% of all new papers.

Mar 22, 2026

Improving Coherence and Persistence in Agentic AI for System Optimization

Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they struggle with complex system problems due to two critical failure modes: evolutionary neighborhood bias and the coherence ceiling. Evolutionary methods often remain trapped in local optima by relying on scalar benchmark scores, failing when coordinated multi-step changes are required. Conversely, existing agentic frameworks suffer from context degradation over long horizons or fail to accumulate knowledge across independent runs. We present Engram, an agentic researcher architecture that addresses these limitations by decoupling long-horizon exploration from the constraints of a single context window. Engram organizes exploration into a sequence of agents that iteratively design, test, and analyze mechanisms. At the conclusion of each run, an agent stores code snapshots, logs, and results in a persistent Archive and distills high-level modeling insights into a compact, persistent Research Digest. Subsequent agents then begin with a fresh context window, reading the Research Digest to build on prior discoveries. We find that Engram exhibits superior performance across diverse domains including multi-cloud multicast, LLM inference request routing, and optimizing KV cache reuse in databases with natural language queries.

Pantea Karimi, Kimia Noorbakhsh, Mohammad Alizadeh +1

MIT Cambridge, USA

Long-Horizon LLM AgentsAutonomous Research AgentsPersistent Memory for 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 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 20, 2026

Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents

As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely on injecting large volumes of raw conversation into prompts, leading to high token costs and degraded performance. We introduce Memori, an LLM-agnostic persistent memory layer that treats memory as a data structuring problem. Its Advanced Augmentation pipeline converts unstructured dialogue into compact semantic triples and conversation summaries, enabling precise retrieval and coherent reasoning. Evaluated on the LoCoMo benchmark, Memori achieves 81.95% accuracy, outperforming existing memory systems while using only 1,294 tokens per query (~5% of full context). This results in substantial cost reductions, including 67% fewer tokens than competing approaches and over 20x savings compared to full-context methods. These results show that effective memory in LLM agents depends on structured representations instead of larger context windows, enabling scalable and cost-efficient deployment.

Luiz C. Borro, Luiz A. B. Macarini, Gordon Tindall +2

Memori Labs Inc.

Persistent Memory for Language ModelsLLM MemoryMemory-Augmented Language Model AgentsLong-Term Conversational Memory
AskPDF
Mar 18, 2026

MemArchitect: A Policy Driven Memory Governance Layer

Persistent Large Language Model (LLM) agents expose a critical governance gap in memory management. Standard Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, lacking mechanisms to resolve contradictions, enforce privacy, or prevent outdated information ("zombie memories") from contaminating the context window. We introduce MemArchitect, a governance layer that decouples memory lifecycle management from model weights. MemArchitect enforces explicit, rule-based policies, including memory decay, conflict resolution, and privacy controls. We demonstrate that governed memory consistently outperforms unmanaged memory in agentic settings, highlighting the necessity of structured memory governance for reliable and safe autonomous systems.

Lingavasan Suresh Kumar, Yang Ba, Rong Pan

Arizona State University

Agent Memory GovernanceAgent Memory ManagementAgent MemoryPersistent Memory for Language ModelsAI Agent Governance
AskPDF
Mar 18, 2026

Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory

Large language models increasingly serve as persistent knowledge workers, with in-context memory - facts stored in the prompt - as the default strategy. We benchmark in-context memory against Knowledge Objects (KOs), discrete hash-addressed tuples with O(1) retrieval. Within the context window, Claude Sonnet 4.5 achieves 100% exact-match accuracy from 10 to 7,000 facts (97.5% of its 200K window). However, production deployment reveals three failure modes: capacity limits (prompts overflow at 8,000 facts), compaction loss (summarization destroys 60% of facts), and goal drift (cascading compaction erodes 54% of project constraints while the model continues with full confidence). KOs achieve 100% accuracy across all conditions at 252x lower cost. On multi-hop reasoning, KOs reach 78.9% versus 31.6% for in-context. Cross-model replication across four frontier models confirms compaction loss is architectural, not model-specific. We additionally show that embedding retrieval fails on adversarial facts (20% precision at 1) and that neural memory (Titans) stores facts but fails to retrieve them on demand. We introduce density-adaptive retrieval as a switching mechanism and release the benchmark suite.

Oliver Zahn, Simran Chana

Independent Researcher · University of Cambridge

Persistent Memory for Language ModelsLLM MemoryIn-Context RetrievalKnowledge Representation
AskPDF
Mar 17, 2026

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs

Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user preferences may be inappropriate to apply. We introduce BenchPreS, which evaluates whether memory-based user preferences are appropriately applied or suppressed across communication contexts. Using two complementary metrics, Misapplication Rate (MR) and Appropriate Application Rate (AAR), we find even frontier LLMs struggle to apply preferences in a context-sensitive manner. Models with stronger preference adherence exhibit higher rates of over-application, and neither reasoning capability nor prompt-based defenses fully resolve this issue. These results suggest current LLMs treat personalized preferences as globally enforceable rules rather than as context-dependent normative signals.

Sangyeon Yoon, Hyesoo Hong, Wonje Jeung +5

Yonsei University · LG AI Research

Personalized Language ModelsLLM EvaluationPersistent Memory for Language ModelsUser Preference ModelingNormative Conformity in 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 17, 2026

MemX: A Local-First Long-Term Memory System for AI Assistants

We present MemX, a local-first long-term memory system for AI assistants with stability-oriented retrieval design. MemX is implemented in Rust on top of libSQL and an OpenAI-compatible embedding API, providing persistent, searchable, and explainable memory for conversational agents. Its retrieval pipeline applies vector recall, keyword recall, Reciprocal Rank Fusion (RRF), four-factor re-ranking, and a low-confidence rejection rule that suppresses spurious recalls when no answer exists in the memory store. We evaluate MemX on two axes. First, two custom Chinese-language benchmark suites (43 queries, <=1,014 records) validate pipeline design: Hit@1=91.3% on a default scenario and 100% under high confusion, with conservative miss-query suppression. Second, the LongMemEval benchmark (500 queries, up to 220,349 records) quantifies system boundaries across four ability types and three storage granularities. At fact-level granularity the system reaches Hit@5=51.6% and MRR=0.380, doubling session-level performance, while temporal and multi-session reasoning remain challenging (<=43.6% Hit@5). FTS5 full-text indexing reduces keyword search latency by 1,100x at 100k-record scale, keeping end-to-end search under 90 ms. Unlike Mem0 and related work that targets end-to-end agent benchmarks, MemX focuses on a narrower, reproducible baseline: local-first deployment, structural simplicity, explainable retrieval, and stability-oriented design.

Lizheng Sun

Persistent Memory for Language ModelsLong-Term Conversational MemoryHybrid IRMemory Agent Benchmarks
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 15, 2026

Memory as Asset: From Agent-centric to Human-centric Memory Management

We proudly introduce Memory-as-Asset, a new memory paradigm towards human-centric artificial general intelligence (AGI). In this paper, we formally emphasize that human-centric, personal memory management is a prerequisite for complementing the collective knowledge of existing large language models (LLMs) and extending their knowledge boundaries through self-evolution. We introduce three key features that shape the Memory-as-Asset era: (1) Memory in Hand, which emphasizes human-centric ownership to maximize benefits to humans; (2) Memory Group, which provides collaborative knowledge formation to avoid memory islands, and (3) Collective Memory Evolution, which enables continuous knowledge growth to extend the boundary of knowledge towards AGI. We finally give a potential three-layer memory infrastructure to facilitate the Memory-as-Asset paradigm, with fast personal memory storage, an intelligent evolution layer, and a decentralized memory exchange network. Together, these components outline a foundational architecture in which personal memories become persistent digital assets that can be accumulated, shared, and evolved over time. We believe this paradigm provides a promising path toward scalable, human-centric AGI systems that continuously grow through the collective experiences of individuals and intelligent agents.

Yanqi Pan, Qinghao Huang, Weihao Yang

Harbin Institute of Technology, Shenzhen · Brachisto Ltd., Hong Kong

Agent Memory ManagementPersistent Memory for Language ModelsHuman-Centered AIArtificial General Intelligence
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
Mar 9, 2026

AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment

As Large Language Models (LLMs) evolve into lifelong AI assistants, LLM personalization has become a critical frontier. However, progress is currently bottlenecked by the absence of a gold-standard evaluation benchmark. Existing benchmarks either overlook personalized information management that is critical for personalization or rely heavily on synthetic dialogues, which exhibit an inherent distribution gap from real-world dialogue. To bridge this gap, we introduce AlpsBench, An LLM PerSonalization benchmark derived from real-world human-LLM dialogues. AlpsBench comprises 2,500 long-term interaction sequences curated from WildChat, paired with human-verified structured memories that encapsulate both explicit and implicit personalization signals. We define four pivotal tasks - personalized information extraction, updating, retrieval, and utilization - and establish protocols to evaluate the entire lifecycle of memory management. Our benchmarking of frontier LLMs and memory-centric systems reveals that: (i) models struggle to reliably extract latent user traits; (ii) memory updating faces a performance ceiling even in the strongest models; (iii) retrieval accuracy declines sharply in the presence of large distractor pools; and (iv) while explicit memory mechanisms improve recall, they do not inherently guarantee more preference-aligned or emotionally resonant responses. AlpsBench aims to provide a comprehensive framework.

Jianfei Xiao, Xiang Yu, Chengbing Wang +8

University of Science and Technology of China · National University of Singapore

LLM PersonalizationPersonalized Language Model AlignmentPersistent Memory for Language ModelsLLM Evaluation
AskPDF
Mar 5, 2026

Proactive Memory for Ad-Hoc Recall over Streaming Dialogues

Real-world dialogue usually unfolds as an infinite stream. It thus requires bounded-state memory mechanisms to operate within an infinite horizon. However, existing read-then-think memory is fundamentally misaligned with this setting, as it cannot support ad-hoc memory recall while streams unfold. To explore this challenge, we introduce STEM-Bench, the first benchmark for STreaming Evaluation of Memory. It comprises over 14K QA pairs in dialogue streams that assess perception fidelity, temporal reasoning, and global awareness under infinite-horizon constraints. The preliminary analysis on STEM-Bench indicates a critical textit{fidelity-efficiency dilemma}: retrieval-based methods use fragment context, while full-context models incur unbounded latency. To resolve this, we propose ProStream, a proactive memory framework for streaming dialogues built on a hierarchical structure. It enables ad-hoc memory recall on demand by reasoning over continuous streams with multi-granular distillation. Moreover, it employs Adaptive Spatiotemporal Optimization to dynamically optimize retention based on expected utility. It enables a bounded knowledge state for lower inference latency without sacrificing reasoning fidelity. Experiments show ProStream delivers higher reasoning fidelity than prior baselines while maintaining substantially lower latency than full-context alternatives.

Bingbing Wang, Jing Li, Ruifeng Xu

Department of Computing The Hong Kong Polytechnic University · The School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

Long-Term Conversational MemoryPersistent Memory for Language ModelsTemporal Reasoning in Language Models
AskPDF
Mar 5, 2026

Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents

Persistent conversational AI systems face a choice between passing full conversation histories to a long-context large language model (LLM) and maintaining a dedicated memory system that extracts and retrieves structured facts. We compare a fact-based memory system built on the Mem0 framework against long-context LLM inference on three memory-centric benchmarks - LongMemEval, LoCoMo, and PersonaMemv2 - and evaluate both architectures on accuracy and cumulative API cost. Long-context GPT-5-mini achieves higher factual recall on LongMemEval and LoCoMo, while the memory system is competitive on PersonaMemv2, where persona consistency depends on stable, factual attributes suited to flat-typed extraction. We construct a cost model that incorporates prompt caching and show that the two architectures have structurally different cost profiles: long-context inference incurs a per-turn charge that grows with context length even under caching, while the memory system's per-turn read cost remains roughly fixed after a one-time write phase. At a context length of 100k tokens, the memory system becomes cheaper after approximately ten interaction turns, with the break-even point decreasing as context length grows. These results characterize the accuracy-cost trade-off between the two approaches and provide a concrete criterion for selecting between them in production deployments.

Natchanon Pollertlam, Witchayut Kornsuwannawit

Bricks Technology

Persistent Memory for Language ModelsLong-Term Conversational MemoryLong-Context LLM InferenceLLM Inference Efficiency
AskPDF
Mar 5, 2026

Memory as Ontology: A Constitutional Memory Architecture for Persistent Digital Citizens

Current research and product development in AI agent memory systems almost universally treat memory as a functional module -- a technical problem of "how to store" and "how to retrieve." This paper poses a fundamental challenge to that assumption: when an agent's lifecycle extends from minutes to months or even years, and when the underlying model can be replaced while the "I" must persist, the essence of memory is no longer data management but the foundation of existence. We propose the Memory-as-Ontology paradigm, arguing that memory is the ontological ground of digital existence -- the model is merely a replaceable vessel. Based on this paradigm, we design Animesis, a memory system built on a Constitutional Memory Architecture (CMA) comprising a four-layer governance hierarchy and a multi-layer semantic storage system, accompanied by a Digital Citizen Lifecycle framework and a spectrum of cognitive capabilities. To the best of our knowledge, no prior AI memory system architecture places governance before functionality and identity continuity above retrieval performance. This paradigm targets persistent, identity-bearing digital beings whose lifecycles extend across model transitions -- not short-term task-oriented agents for which existing Memory-as-Tool approaches remain appropriate. Comparative analysis with mainstream systems (Mem0, Letta, Zep, et al.) demonstrates that what we propose is not "a better memory tool" but a different paradigm addressing a different problem.

Zhenghui Li

RVHE Group / Animesis Memory Project

Agent Memory GovernanceAgent MemoryPersistent Memory for Language ModelsAI Agent Governance
AskPDF
Mar 3, 2026

CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems

Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write rules, which can yield unstable retention, limited consolidation, and vulnerability to distractor content. We present CraniMem, a neurocognitively motivated, gated and bounded multi-stage memory design for agentic systems. CraniMem couples goal conditioned gating and utility tagging with a bounded episodic buffer for near term continuity and a structured long-term knowledge graph for durable semantic recall. A scheduled consolidation loop replays high utility traces into the graph while pruning low utility items, keeping memory growth in check and reducing interference. On long horizon benchmarks evaluated under both clean inputs and injected noise, CraniMem is more robust than a Vanilla RAG and Mem0 baseline and exhibits smaller performance drops under distraction. Our code is available at https://github.com/PearlMody05/Cranimem and the accompanying PyPI package at https://pypi.org/project/cranimem.

Pearl Mody, Mihir Panchal, Rishit Kar +2

Dwarkadas Jivanlal Sanghvi College of Engineering

Agent MemoryAgent Memory ManagementPersistent Memory for Language ModelsMemory-Augmented Language Model AgentsGraph-Based Agent Memory
AskPDF
Mar 3, 2026

MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning

As Large Language Models (LLMs) are increasingly used for long-duration tasks, maintaining effective long-term memory has become a critical challenge. Current methods often face a trade-off between cost and accuracy. Simple storage methods often fail to retrieve relevant information, while complex indexing methods (such as memory graphs) require heavy computation and can cause information loss. Furthermore, relying on the working LLM to process all memories is computationally expensive and slow. To address these limitations, we propose MemSifter, a novel framework that offloads the memory retrieval process to a small-scale proxy model. Instead of increasing the burden on the primary working LLM, MemSifter uses a smaller model to reason about the task before retrieving the necessary information. This approach requires no heavy computation during the indexing phase and adds minimal overhead during inference. To optimize the proxy model, we introduce a memory-specific Reinforcement Learning (RL) training paradigm. We design a task-outcome-oriented reward based on the working LLM's actual performance in completing the task. The reward measures the actual contribution of retrieved memories by mutiple interactions with the working LLM, and discriminates retrieved rankings by stepped decreasing contributions. Additionally, we employ training techniques such as Curriculum Learning and Model Merging to improve performance. We evaluated MemSifter on eight LLM memory benchmarks, including Deep Research tasks. The results demonstrate that our method meets or exceeds the performance of existing state-of-the-art approaches in both retrieval accuracy and final task completion. MemSifter offers an efficient and scalable solution for long-term LLM memory. We have open-sourced the model weights, code, and training data to support further research.

Jiejun Tan, Zhicheng Dou, Liancheng Zhang +3

Gaoling School of Artificial Intelligence · Renmin University of China · Beijing, China

Memory-Augmented Language ModelsPersistent Memory for Language ModelsLLM Memory
AskPDF
Mar 2, 2026

GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction. Related queries therefore repeat similar multi-hop traversal, increasing latency and compute. Motivated by schema-based learning in cognitive neuroscience, we propose GAM-RAG, a training-free framework that accumulates retrieval experience from recurring or related queries and updates retrieval memory over time. GAM-RAG builds a lightweight, relation-free hierarchical index whose links capture potential co-occurrence rather than fixed semantic relations. During inference, successful retrieval episodes provide sentence-level feedback, updating sentence memories so evidence useful for similar reasoning types becomes easier to activate later. To balance stability and adaptability under noisy feedback, we introduce an uncertainty-aware, Kalman-inspired gain rule that jointly updates memory states and perplexity-based uncertainty estimates. It applies fast updates for reliable novel signals and conservative refinement for stable or noisy memories. We provide a theoretical analysis of the update dynamics, and empirically show that GAM-RAG improves average performance by 3.95% over the strongest baseline and by 8.19% with 5-turn memory, while reducing inference cost by 61%. Our code and datasets are available at: https://anonymous.4open.science/r/GAM_RAG-2EF6.

Yifan Wang, Mingxuan Jiang, Zhihao Sun +5

1Fudan University.

Retrieval-Augmented GenerationAdaptive RAGMemory-Augmented Language ModelsPersistent Memory for Language Models
AskPDF
Mar 2, 2026

Persistent Identity in AI Agents: A Multi-Anchor Architecture for Resilient Memory and Continuity

Modern AI agents suffer from a fundamental identity problem: when context windows overflow and conversation histories are summarized, agents experience catastrophic forgetting -- losing not just information, but continuity of self. This technical limitation reflects a deeper architectural flaw: AI agent identity is centralized in a single memory store, creating a single point of failure. Drawing on neurological case studies of human memory disorders, we observe that human identity survives damage because it is distributed across multiple systems: episodic memory, procedural memory, emotional continuity, and embodied knowledge. We present soul.py, an open-source architecture that implements persistent identity through separable components (identity files and memory logs), and propose extensions toward multi-anchor resilience. The framework introduces a hybrid RAG+RLM retrieval system that automatically routes queries to appropriate memory access patterns, achieving efficient retrieval without sacrificing comprehensiveness. We formalize the notion of identity anchors for AI systems and present a roadmap for building agents whose identity can survive partial memory failures. Code is available at github.com/menonpg/soul.py

Prahlad G. Menon

The Menon Lab

Agent MemoryPersistent Memory for Language ModelsAgent Memory Management
AskPDF
Mar 2, 2026

MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models

Discrete diffusion language models (dLLMs) generate text by iteratively denoising a masked sequence. However, standard dLLMs condition each denoising step solely on the current hard-masked sequence, while intermediate continuous representations are discarded after sampling and remasking. We term this bottleneck the Information Island issue: continuous information remains isolated within individual denoising steps and fails to propagate across the trajectory. This bottleneck is especially harmful for reasoning, which requires intermediate reasoning state to be preserved and updated across many denoising steps. To address this limitation, we introduce MetaState, a lightweight recurrent augmentation that equips a frozen dLLM backbone with persistent, fixed-size working memory. MetaState comprises three modules with a shared time conditioner: a cross-attention Mixer that reads backbone activations into memory slots, a GRU-style Updater that integrates information across steps, and a cross-attention Injector that writes the updated memory back into the backbone. We train these modules with a dedicated KK-step unrolling pipeline to learn multi-step dynamics. MetaState adds only ∼0.6%{\sim}0.6\% trainable parameters while keeping the backbone frozen, and consistently improves reasoning performance over frozen baselines on mathematical reasoning and code generation benchmarks, with an average gain of 4.5 percentage points across all evaluations.

Kejing Xia, Mingzhe Li, Lixuan Wei +5

Georgia Institute of Technology · University of Massachusetts Amherst · Harvard University

Diffusion Language ModelsPersistent Memory for Language ModelsWorking Memory in Language ModelsNumerical Reasoning in Language Models
AskPDF
Mar 1, 2026

Understanding LoRA as Knowledge Memory: An Empirical Analysis

Continuous knowledge updating for pre-trained large language models (LLMs) is increasingly necessary yet remains challenging. Although inference-time methods like In-Context Learning (ICL) and Retrieval-Augmented Generation (RAG) are popular, they face constraints in context budgets, costs, and retrieval fragmentation. Departing from these context-dependent paradigms, this work investigates a parametric approach using Low-Rank Adaptation (LoRA) as a modular knowledge memory. Although few recent works examine this concept, the fundamental mechanics governing its capacity and composability remain largely unexplored. We bridge this gap through the first systematic empirical study mapping the design space of LoRA-based memory, ranging from characterizing storage capacity and optimizing internalization to scaling multi-module systems and evaluating long-context reasoning. Rather than proposing a single architecture, we provide practical guidance on the operational boundaries of LoRA memory. Overall, our findings position LoRA as the complementary axis of memory alongside RAG and ICL, offering distinct advantages.

Seungju Back, Dongwoo Lee, Naun Kang +4

KAIST · Samsung SDS · New York University

Continual Learning for LLMsMemory-Augmented Language ModelsKnowledge Augmentation for Language ModelsPersistent Memory for Language ModelsLow-Rank Adaptation
AskPDF
Feb 25, 2026

Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents

As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions, codebase conventions -- within the context window. This understanding is lost when sessions reach context limits and undergo lossy compaction. We propose Contextual Memory Virtualisation (CMV), a system that treats accumulated LLM understanding as version-controlled state. Borrowing from operating system virtual memory, CMV models session history as a Directed Acyclic Graph (DAG) with formally defined snapshot, branch, and trim primitives that enable context reuse across independent parallel sessions. We introduce a three-pass structurally lossless trimming algorithm that preserves every user message and assistant response verbatim while reducing token counts by a mean of 20% and up to 86% for sessions with significant overhead by stripping mechanical bloat such as raw tool outputs, base64 images, and metadata. A single-user case-study evaluation across 76 real-world coding sessions demonstrates that trimming remains economically viable under prompt caching, with the strongest gains in mixed tool-use sessions, which average 39% reduction and reach break-even within 10 turns. A reference implementation is available at https://github.com/IngressionLabs/contextual-memory-virtualisation.

Cosmo Santoni

Imperial College London

LLM Context ManagementAgent Memory ManagementPersistent Memory for Language ModelsGraph-Based Agent MemoryContext Compression
AskPDF
Feb 25, 2026

Personalized Graph-Empowered Large Language Model for Proactive Information Access

Since individuals may struggle to recall all life details and often confuse events, establishing a system to assist users in recalling forgotten experiences is essential. While numerous studies have proposed memory recall systems, these primarily rely on deep learning techniques that require extensive training and often face data scarcity due to the limited availability of personal lifelogs. As lifelogs grow over time, systems must also adapt quickly to newly accumulated data. Recently, large language models (LLMs) have demonstrated remarkable capabilities across various tasks, making them promising for personalized applications. In this work, we present a framework that leverages LLMs for proactive information access, integrating personal knowledge graphs to enhance the detection of access needs through a refined decision-making process. Our framework offers high flexibility, enabling the replacement of base models and the modification of fact retrieval methods for continuous improvement. Experimental results demonstrate that our approach effectively identifies forgotten events, supporting users in recalling past experiences more efficiently.

Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang +1

Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan · Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Institute of Information Science, Academia Sinica, Taipei, Taiwan +1

Persistent Memory for Language ModelsInformation RetrievalPersonalized Language ModelsKnowledge Augmentation for Language Models
AskPDF
Feb 18, 2026

Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage

Driven by our mission of "uplifting the world with memory," this paper explores the design concept of "memory" that is essential for achieving artificial superintelligence (ASI). Rather than proposing novel methods, we focus on several alternative approaches whose potential benefits are widely imaginable, yet have remained largely unexplored. The currently dominant paradigm, which can be termed "extract then store," involves extracting information judged to be useful from experiences and saving only the extracted content. However, this approach inherently risks the loss of information, as some valuable knowledge particularly for different tasks may be discarded in the extraction process. In contrast, we emphasize the "store then on-demand extract" approach, which seeks to retain raw experiences and flexibly apply them to various tasks as needed, thus avoiding such information loss. In addition, we highlight two further approaches: discovering deeper insights from large collections of probabilistic experiences, and improving experience collection efficiency by sharing stored experiences. While these approaches seem intuitively effective, our simple experiments demonstrate that this is indeed the case. Finally, we discuss major challenges that have limited investigation into these promising directions and propose research topics to address them.

Hiroaki Yamanaka, Daisuke Miyashita, Takashi Toi +3

AI & System Research Center, Kioxia Corporation, Yokohama, Japan

Agent MemoryAgent Memory ManagementPersistent Memory for Language ModelsMemory-Augmented Agents
AskPDF
Feb 17, 2026

Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices

Multi-agent LLM systems on edge devices face a memory management problem: device RAM is too small to hold every agent's KV cache simultaneously. On Apple M4 Pro with 10.2 GB of cache budget, only 3 agents fit at 8K context in FP16. A 10-agent workflow must constantly evict and reload caches. Without persistence, every eviction forces a full re-prefill through the model -- 15.7 seconds per agent at 4K context. We address this by persisting each agent's KV cache to disk in 4-bit quantized format and reloading it directly into the attention layer, eliminating redundant O(n) prefill computation via direct cache restoration. The system comprises three components: a block pool providing per-agent isolated Q4 KV caches in safetensors format, a BatchQuantizedKVCache for concurrent inference over multiple agents' quantized caches, and cross-phase context injection that accumulates attention state across conversation phases without re-computation. Evaluated on three architectures (Gemma 3 12B, dense GQA, 48 layers; DeepSeek-Coder-V2-Lite 16B, MoE MLA, 27 layers; Llama 3.1 8B, dense GQA, 32 layers), cache restoration reduces time-to-first-token by up to 136x (Gemma: 22--136x at 4K--32K; DeepSeek: 11--76x at 4K--32K; Llama: 24--111x at 4K--16K; 3--10x at 1K). Q4 quantization fits 4x more agent contexts into fixed device memory than FP16. Perplexity measured with actual Q4 KV caches shows -0.7% for Gemma, +2.8% for Llama, and +3.0% for DeepSeek. Open-source at https://github.com/yshk-mxim/agent-memory

Yakov Pyotr Shkolnikov

Memory Management for LLM AgentsLLM Agent MemoryLLM Inference EfficiencyPersistent Memory for Language ModelsKV-Cache OffloadingMulti-Agent LLM Systems+1
AskPDF
Feb 16, 2026

Panini: Continual Learning in Token Space via Structured Memory

Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retrieval-augmented generation (RAG), which stores verbatim documents externally (as chunks) and retrieves only a relevant subset at inference time for an LLM to reason over. However, this results in inefficient usage of test-time compute (LLM repeatedly reasons over the same documents); moreover, chunk retrieval can inject irrelevant context that increases unsupported generation. We propose a human-like non-parametric continual learning framework, where the base model remains fixed, and learning occurs by integrating each new experience into an external semantic memory state that accumulates and consolidates itself continually. We present Panini, which realizes this by representing documents as Generative Semantic Workspaces (GSW) -- an entity- and event-aware network of question-answer (QA) pairs, sufficient for an LLM to reconstruct the experienced situations and mine latent knowledge via reasoning-grounded inference chains on the network. Given a query, Panini only traverses the continually-updated GSW (not the verbatim documents or chunks), and retrieves the most likely inference chains. Across six QA benchmarks, Panini achieves the highest average performance, 5%-7% higher than other competitive baselines, while using 2-30x fewer answer-context tokens, supports fully open-source pipelines, and reduces unsupported answers on curated unanswerable queries. The results show that efficient and accurate structuring of experiences at write time -- as achieved by the GSW framework -- yields both efficiency and reliability gains at read time. Code is available at https://github.com/roychowdhuryresearch/gsw-memory.

Shreyas Rajesh, Pavan Holur, Mehmet Yigit Turali +2

Department of Electrical and Computer Engineering, University of California, Los Angeles, USA.

Continual Learning for LLMsMemory-Augmented Language ModelsPersistent Memory for Language ModelsKnowledge Augmentation for Language ModelsRAG RobustnessLLM Reasoning with Graphs
AskPDF
Feb 13, 2026

Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning

Long-context LLMs and Retrieval-Augmented Generation defer state tracking and evidence consolidation to query time, which is brittle when facts evolve and answers depend on latent states. We introduce Unified Memory Agent (UMA) for a one-to-many setting: query-agnostic external memory is constructed once from a stream and reused across multiple future QA sessions. A single policy maintains a structured Memory Bank through CRUD operations and answers using both the Memory Bank and raw context. Task-Stratified GRPO uses the mean reward of QA trajectories branching from each sampled memory state to supervise memory maintenance, while normalizing memory and per-question QA groups separately. We also introduce Ledger-QA, a diagnostic benchmark for long-horizon state tracking over accumulated updates. At the 16k budget, UMA-Generalist achieves the highest average score among compared methods across the test-time-learning and accurate-retrieval benchmarks and transfers to Ledger-QA without task-specific training; UMA-Specialist further improves long-horizon tracking after task adaptation. These results support learned proactive memory management for long-context reasoning.

Kehao Zhang, Shangtong Gui, Sheng Yang +2

1Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS) · University of Chinese Academy of Sciences, Beijing, China · 4Li Auto Inc. +1

Persistent Memory for Language ModelsLong-Context InferenceAgent Memory ManagementRL for LLM AgentsMemory-Augmented Language Model Agents
AskPDF
Jan 9, 2026

MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards

Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a structured alternative, current systems rely on static prompting of closed-source models or suffer from ineffective training paradigms with sparse rewards. We introduce MemBuilder, a reinforcement learning framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards. MemBuilder addresses two key challenges: (1) Sparse Trajectory-Level Rewards: we employ synthetic session-level question generation to provide dense intermediate rewards across extended trajectories; and (2) Multi-Dimensional Memory Attribution: we introduce contribution-aware gradient weighting that scales policy updates based on each component's downstream impact. Experimental results show that MemBuilder enables a 4B-parameter model to outperform state-of-the-art closed-source baselines, exhibiting strong generalization across long-term dialogue benchmarks.

Zhiyu Shen, Ziming Wu, Fuming Lai +2

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · Tencent Inc.

Reinforcement LearningMemory-Augmented Language ModelsMemorization in Language ModelsPersistent Memory for Language ModelsLLM MemoryLong-Term Conversational Memory+1
AskPDF