Agent Memory Management

Ask about this topic

Overview

It gives language and embodied agents persistent state beyond a context window, supporting personalization, multi-step work, and adaptation as facts change. Systems range from raw-log and vector-search stores to episodic-semantic hierarchies, temporal or provenance-aware graphs, and learned controllers that decide what to write, retrieve, consolidate, or discard. Evaluations use long-dialogue question answering benchmarks such as LoCoMo and LongMemEval, alongside tool-use, coding, and GUI tasks, measuring accuracy as well as token cost, latency, retention, and stale or unsafe recall. The central challenge is balancing useful evidence and traceability against bounded storage and computation: retention cannot help if retrieval fails, while compression, updates, and sharing can lose, stale, or expose information, and no design works best across all workloads.

Latest papers

CardsList

449 papers68 papers in the last four weeks, up 8% on the four weeks before. 0.4% of all new papers.

May 1, 2026

MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents

Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that decouples memory admission from the downstream answer backbone and replaces per-turn memory-management decoding with an embedding-based routing policy. MemRouter encodes each turn together with recent context, projects the resulting embeddings through a frozen LLM backbone, and predicts whether the turn should be stored using lightweight classification heads while training only 12M parameters. Under a controlled matched-harness comparison on LoCoMo, where the retrieval pipeline, answer prompts, and QA backbone (Qwen2.5-7B) are held identical, MemRouter outperforms an LLM-based memory manager on every question category (overall F1 52.0 vs 45.6, non-overlapping 95% CIs) while reducing memory-management p50 latency from 970ms to 58ms. Descriptive factorial averaging further shows that learned admission improves mean F1 by +10.3 over random storage, category-specific prompting adds +5.2 over a generic prompt, and retrieval contributes +0.7. These results suggest that write-side memory admission can be learned by a small supervised router, while answer generation remains a separate downstream component in long-horizon conversational QA.

Tianyu Hu, Weikai Lin, Weizhi Zhang +2

University of Central Florida · University of Rochester · University of Illinois at Chicago +1

Persistent Memory for Language ModelsLong-Term Conversational MemoryAgent Memory Management
AskPDF
Apr 30, 2026

From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction

Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismatched to the kinds of memory that agents need in production: exact facts, current state, updates and deletions, aggregation, relations, negative queries, and explicit unknowns. These operations require memory to behave less like search and more like a system of record. This paper argues that reliable external AI memory must be schema-grounded. Schemas define what must be remembered, what may be ignored, and which values must never be inferred. We present an iterative, schema-aware write path that decomposes memory ingestion into object detection, field detection, and field-value extraction, with validation gates, local retries, and stateful prompt control. The result shifts interpretation from the read path to the write path: reads become constrained queries over verified records rather than repeated inference over retrieved prose. We evaluate this design on structured extraction and end-to-end memory benchmarks. On the extraction benchmark, the judge-in-the-loop configuration reaches 90.42% object-level accuracy and 62.67% output accuracy, above all tested frontier structured-output baselines. On our end-to-end memory benchmark, xmemory reaches 97.10% F1, compared with 80.16%-87.24% across the third-party baselines. On the application-level task, xmemory reaches 95.2% accuracy, outperforming specialised memory systems, code-generated Markdown harnesses, and customer-facing frontier-model application harnesses. The results show that, for memory workloads requiring stable facts and stateful computation, architecture matters more than retrieval scale or model strength alone.

Alex Petrov, Alexander Gusak, Denis Mukha +1

1xmemory

LLM MemoryDocument Information ExtractionLLM Information ExtractionAgent Memory Management
AskPDF
Apr 30, 2026

Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents

Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved memory is useful only when the current failure is genuinely compatible with a previous one; superficial similarity in stack traces, terminal errors, paths, or configuration symptoms can lead to unsafe memory injection. This paper reframes issue-memory use as a selective, risk-sensitive control problem rather than a pure top-k retrieval problem. We introduce RSCB-MC, a risk-sensitive contextual bandit memory controller that decides whether an agent should use no memory, inject the top resolution, summarize multiple candidates, perform high-precision or high-recall retrieval, abstain, or ask for feedback. The system stores reusable issue knowledge through a pattern-variant-episode schema and converts retrieval evidence into a fixed 16-feature contextual state capturing relevance, uncertainty, structural compatibility, feedback history, false-positive risk, latency, and token cost. Its reward design penalizes false-positive memory injection more strongly than missed reuse, making non-injection and abstention first-class safety actions. In deterministic smoke-scale artifacts, RSCB-MC obtains the strongest non-oracle offline replay success rate, 62.5%, while maintaining a 0.0% false-positive rate. In a bounded 200-case hot-path validation, it reaches 60.5% proxy success with 0.0% false positives and a 331.466 microseconds p95 decision latency. The results show that, for coding-agent memory, the key question is not only which memory is most similar, but whether any retrieved memory is safe enough to influence the debugging trajectory.

Mehmet Iscan

PythaLab, Yildiz Technical University, Istanbul, Türkiye.

Selective PredictionAI Coding AgentsLLM Agent MemoryContextual BanditsAgent Memory Management
AskPDF
Apr 29, 2026

Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture

As Large Language Model (LLM) agents transition from single-session tools to persistent systems managing longitudinal healthcare journeys, their memory architectures face a critical challenge: reconciling two imperfect sources of truth. The patient's evolving self-report is current but prone to recall bias, while the Electronic Health Record (EHR) is medically validated but frequently stale. General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement, a pattern that risks safety failures when applied to clinical data. We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record (FHIR), governed by a dedicated Reconciliation Engine that evaluates every extracted memory against the patient's FHIR profile and classifies discrepancies by type, severity, and the specific FHIR resources involved. We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions, using a hybrid dataset that interleaves real provider-patient transcripts with synthetic, FHIR-grounded clinical scenarios. In isolated testing, the engine detects 84.4% of designed clinical discrepancies with 86.7% safety-critical recall. By coupling extraction and reconciliation evaluation on the same data, we directly quantify a 13.6% error cascade, tracing the degradation to clinical details lost during memory extraction from unstructured conversation rather than to downstream classification errors. These findings establish that validating patient-reported memories against clinical records is both feasible and necessary for safe deployment of longitudinal health agents.

Samuel L Pugh, Eric Yang, Alexander Muir Sutherland +1

Verily Health Inc.

Long-Term Conversational MemoryAgent Memory ManagementMemory-Augmented Language Model Agents
AskPDF
Apr 29, 2026

OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory

Autonomous LLM agents increasingly operate in long-horizon, interactive settings where success depends on reusing experience accumulated over extended histories. However, existing agent memory systems are fundamentally constrained by text-context budgets: storing or revisiting raw trajectories is prohibitively token-expensive, while summarization and text-only retrieval trade token savings for information loss and fragmented evidence. To address this limitation, we propose Optical Context Retrieval Memory (OCR-Memory), a memory framework that leverages the visual modality as a high-density representation of agent experience, enabling retention of arbitrarily long histories with minimal prompt overhead at retrieval time. Specifically, OCR-Memory renders historical trajectories into images annotated with unique visual identifiers. OCR-Memory retrieves stored experience via a locate-and-transcribe paradigm that selects relevant regions through visual anchors and retrieves the corresponding verbatim text, avoiding free-form generation and reducing hallucination. Experiments on long-horizon agent benchmarks show consistent gains under strict context limits, demonstrating that optical encoding increases effective memory capacity while preserving faithful evidence recovery.

Jinze Li, Yang Zhang, Xin Yang +5

The University of Hong Kong · University of North Texas · University of Tsukuba +1

Agent MemoryAgent Memory ManagementMemory-Augmented Language Model Agents
AskPDF
Apr 29, 2026

When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric learning. We show that this challenge does not disappear but resurfaces at the memory level. Under a limited context window, old and new experiences compete during retrieval, relocating the continual-learning bottleneck from parameter updates to memory access. To study this phenomenon, we introduce a (k,v) framework that disentangles two fundamental design axes of external memory: how experience is represented and how it is organized for retrieval. Across sequential-task experiments in ALFWorld and BabyAI, we find that abstract procedural memories transfer more reliably than detailed trajectories, while negative transfer disproportionately harms the hard cases. Moreover, finer-grained memory organization is not universally beneficial: designs that yield strong forward transfer can simultaneously induce severe forgetting. Together, these results reveal that external memory does not resolve the continual-learning problem; it reshapes it into a problem of memory representation and retrieval design.

Qisheng Hu, Quanyu Long, Wenya Wang

Nanyang Technological University

Continual Learning for LLM AgentsLLM Agent MemoryTransfer LearningAgent Memory ManagementCatastrophic ForgettingMemory-Augmented Language Model Agents
AskPDF
Apr 29, 2026

Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent

Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential. A central enabler of such capabilities is the agent's long-term semantic memory system, which extracts implicit and explicit signals from noisy longitudinal behavioral data, stores them in a structured form, and supports low-latency retrieval. Building industrial-grade long-term memory for LLM agents raises five challenges: scalability, low-latency retrieval, privacy constraints, adaptability, and observability. We introduce the Hierarchical Long-Term Semantic Memory (HLTM) framework, which organizes textual data into a schema-aligned memory tree that captures semantic knowledge at multiple levels of granularity, enabling scalable ingestion, privacy-aware storage, low-latency retrieval, and transparent provenance; HLTM further incorporates an adaptation mechanism to generalize across diverse use cases. Extensive evaluations on LinkedIn's Hiring Assistant show that HLTM improves answer correctness by more than 5% and retrieval F1 by more than 10%, while significantly advancing the Pareto frontier between query and indexing latency. HLTM has been fully deployed in LinkedIn's Hiring Assistant to power core personalization features in production hiring workflows.

Zhentao Xu, Shangjin Zhang, Emir Poyraz +7

LinkedIn Corporation Sunnyvale, CA, USA · LinkedIn Corporation New York, NY, USA

LLM Agent MemoryPersistent Memory for Language ModelsAgent Memory Management
AskPDF
Apr 26, 2026

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

On LongMemEval-500, ZenBrain matches a long-context oracle's binary-judge accuracy to within 4.5 pp (47.7%47.7\% vs. 52.2%52.2\%; 91.3%91.3\%) at 1/106th1/106^\text{th} of the per-query token cost (App. F.5-F.6, Fig. 2), and wins all 12 head-to-head answer-quality cells (4 systems ×\times 3 LLM judges) against Letta, Mem0, and A-Mem under Bonferroni correction (α=0.05/18α=0.05/18, pmin=6.2×10−31p_\text{min}=6.2\times 10^{-31}, d∈[0.18,0.52]d \in [0.18, 0.52]). ZenBrain is a 7-layer neuroscience-inspired memory architecture. The contribution is architectural integration: 15 validated neuroscience mechanisms unified under a single MemoryCoordinator -- 9 foundational algorithms (Two-Factor Synaptic KG, vmPFC-coupled FSRS, Simulation-Selection sleep, Bayesian confidence, and five more) plus 6 Predictive Memory Architecture components (NeuromodulatorEngine, ReconsolidationEngine, TripleCopyMemory, PriorityMap, StabilityProtector, MetacognitiveMonitor). No prior system integrates more than two. Stress ablation (60 days, Wilcoxon, 10 seeds) reveals a cooperative survival network: 9 of 15 mechanisms become individually critical (ΔQΔQ up to −93.7%-93.7\%), while moderate conditions mask individual contributions. Sim-Selection sleep adds 37% stability with 47.4% storage reduction (p≤5.1×10−3p \le 5.1\times 10^{-3}); TripleCopyMemory retains S(t)=0.912S(t)=0.912 at 30 days; multi-layer routing beats a flat baseline by +20.7%+20.7\% F1 on LoCoMo, +19.5%+19.5\% on MemoryArena. A cross-provider bias-direction check (ΔGPT-Anth=−0.0001Δ_\text{GPT-Anth}=-0.0001 for ZB vs. −0.049-0.049 for Mem0) rules out LLM-judge-specific confounds. Open-source with 11,589 CI tests.

Alexander Bering

Zensation AI

Memorization in Language ModelsNeural ProcessesPersistent Memory for Language ModelsLong-Term Conversational MemoryMemory-Augmented AgentsAgent Memory Management
AskPDF
Apr 24, 2026

ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents

Large language model (LLM) agents often struggle in long-context interactions. As the history grows, sliding windows and prompt compression may drop earlier information that later steps rely on. Retrieval-based memory systems surface relevant content but still overlook the causal and logical dependencies between steps. We introduce ContextWeaver, a selective and dependency-structured memory framework that organizes an agent's interaction trace into a graph of reasoning steps and selects the relevant context for future actions. ContextWeaver supports (1) dependency-based construction and traversal that link each step to the earlier steps it relies on; (2) compact dependency summaries of the reasoning paths; and (3) a lightweight validation layer that incorporates execution feedback. On five software-engineering and terminal benchmarks with a fixed budget per task, ContextWeaver improves the resolve rate over a sliding-window baseline on all five, with a significant gain when pooled across benchmarks, while using 13-18% fewer agent steps. It also performs favorably against alternative context-management approaches, with the largest gains on long-horizon repository tasks. On SWE-Bench Pro, ContextWeaver raises the resolve rate from 66.5% to 72.6%, with significant improvements across all three model backbones. The improvement also holds when the sliding window's budget is raised to cover the summary cost.

Yating Wu, Yuhao Zhang, Sayan Ghosh +4

UT Austin · AWS AI Labs

LLM Agent MemoryGraph-Based Agent MemoryLLM Context ManagementAgent Memory Management
AskPDF
Apr 23, 2026

Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies largely depend on hybrid semantic graph architectures, which impose substantial computational overhead during both ingestion and retrieval. These systems typically require large language model mediated entity extraction, explicit graph schema maintenance, and multi query retrieval pipelines. This paper introduces Memanto, a universal memory layer for agentic artificial intelligence that challenges the prevailing assumption that knowledge graph complexity is necessary to achieve high fidelity agent memory. Memanto integrates a typed semantic memory schema comprising thirteen predefined memory categories, an automated conflict resolution mechanism, and temporal versioning. These components are enabled by Moorcheh's Information Theoretic Search engine, a no indexing semantic database that provides deterministic retrieval within sub ninety millisecond latency while eliminating ingestion delay. Through systematic benchmarking on the LongMemEval and LoCoMo evaluation suites, Memanto achieves state of the art accuracy scores of 89.8 percent and 87.1 percent respectively. These results surpass all evaluated hybrid graph and vector based systems while requiring only a single retrieval query, incurring no ingestion cost, and maintaining substantially lower operational complexity. A five stage progressive ablation study is presented to quantify the contribution of each architectural component, followed by a discussion of the implications for scalable deployment of agentic memory systems.

Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel +3

Moorcheh AI EdgeAI Innovations

Agent MemoryInformation RetrievalLong-Term Conversational MemoryAgent Memory Management
AskPDF
Apr 22, 2026

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and Ebbinghaus forgetting curve)--remains underexplored. We argue that in resource-constrained environments, a well-designed forgetting mechanism is as crucial as remembering, delivering benefits across three dimensions: (1) efficiency via intelligent memory pruning, (2) quality by dynamically updating outdated preferences and context, and (3) security through active forgetting of malicious inputs, sensitive data, and privacy-compromising content. Our framework establishes a taxonomy of forgetting mechanisms: passive decay-based, active deletion-based, safety-triggered, and adaptive reinforcement-based. Building on advances in LLM agent architectures and vector databases, we present detailed specifications, implementation strategies, and empirical validation from controlled experiments. Results show significant improvements: access efficiency (+8.49%), content quality (+29.2% signal-to-noise ratio), and security performance (100% elimination of security risks). Our work bridges cognitive neuroscience and AI systems, offering practical solutions for real-world deployment while addressing ethical and regulatory compliance. The paper concludes with challenges and future directions, establishing selective forgetting as a fundamental capability for next-generation LLM agents operating in real-world, resource-constrained scenarios. Our contributions align with AI-native memory systems and responsible AI development.

Yingjie Gu, Wenjian Xiong, Liqiang Wang +7

China Mobile Digital Intelligence Business Unit | China Mobile Jiutian Company | China Mobile Jiutian Research Institute

LLM Agent SecurityMemory-Augmented AgentsAgent Memory Management
AskPDF
Apr 22, 2026

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving

Large Language Models (LLMs) often struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but conflicting modeling paradigms, hindering effective solution generation. To address this, we propose Dual-Cluster Memory Agent (DCM-Agent) to enhance performance by leveraging historical solutions in a training-free manner. Central to this is Dual-Cluster Memory Construction. This agent assigns historical solutions to modeling and coding clusters, then distills each cluster's content into three structured types: Approach, Checklist, and Pitfall. This process derives generalizable guidance knowledge. Furthermore, this agent introduces Memory-augmented Inference to dynamically navigate solution paths, detect and repair errors, and adaptively switch reasoning paths with structured knowledge. The experiments across seven optimization benchmarks demonstrate that DCM-Agent achieves an average performance improvement of 11%- 21%. Notably, our analysis reveals a ``knowledge inheritance'' phenomenon: memory constructed by larger models can guide smaller models toward superior performance, highlighting the framework's scalability and efficiency.

Xinyu Zhang, Yuchen Wan, Boxuan Zhang +4

School of Computer Science and Technology, Xi’an Jiaotong University · 2Ministry of Education Key Laboratory of Intelligent Networks and Network Security, China · 3Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, China

Large Language Model-Guided OptimizationAgent Memory ManagementMemory-Augmented Language Model Agents
AskPDF
Apr 22, 2026

To Know is to Construct: Schema-Constrained Generation for Agent Memory

Constructivist epistemology argues that knowledge is actively constructed rather than passively copied. Despite the generative nature of Large Language Models (LLMs), most existing agent memory systems are still based on dense retrieval. However, dense retrieval heavily relies on semantic overlap or entity matching within sentences. Consequently, embeddings often fail to distinguish instances that are semantically similar but contextually distinct, introducing substantial noise by retrieving context-mismatched entries. Conversely, directly employing open-ended generation for memory access risks "Structural Hallucination" where the model generates memory keys that do not exist in the memory, leading to lookup failures. Inspired by this epistemology, we posit that memory is fundamentally organized by cognitive schemas, and valid recall must be a generative process performed within these schematic structures. To realize this, we propose SCG-MEM, a schema-constrained generative memory architecture. SCG-MEM reformulates memory access as Schema-Constrained Generation. By maintaining a dynamic Cognitive Schema, we strictly constrain LLM decoding to generate only valid memory entry keys, providing a formal guarantee against structural hallucinations. To support long-term adaptation, we model memory updates via assimilation (grounding inputs into existing schemas) and accommodation (expanding schemas with novel concepts). Furthermore, we construct an Associative Graph to enable multi-hop reasoning through activation propagation. Experiments on the LoCoMo benchmark show that SCG-MEM substantially improves performance across all categories over retrieval-based baselines.

Lei Zheng, Weinan Song, Daili Li +1

UnionPay

Schema-Constrained GenerationLong-Term Conversational MemoryAssociative MemoryAgent Memory ManagementText Generation
AskPDF
Apr 21, 2026

From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact retrieval from past conversations, providing limited insight into agents' ability to consolidate memory over time or handle frequent knowledge updates. We introduce Memora, a long-term memory benchmark spanning weeks to months long user conversations. The benchmark evaluates three memory-grounded tasks: remembering, reasoning, and recommending. To ensure data quality, we employ automated memory-grounding checks and human evaluation. We further introduce Forgetting-Aware Memory Accuracy (FAMA), a metric that penalizes reliance on obsolete or invalidated memory when evaluating long-term memory. Evaluations of four LLMs and six memory agents reveal frequent reuse of invalid memories and failures to reconcile evolving memories. Memory agents offer marginal improvements, exposing shortcomings in long-term memory for personalized agents.

Md Nayem Uddin, Kumar Shubham, Eduardo Blanco +2

Arizona State University · Genies · University of Arizona

Long-Horizon Agent EvaluationAI Agent BenchmarksMemory Agent BenchmarksLong-Term Conversational MemoryAgent Memory Management
AskPDF
Apr 21, 2026

Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems

Teams of LLM agents increasingly collaborate on tasks spanning days or weeks: multi-day data-generation sprints where generator, reviewer, and auditor agents coordinate in real time on overlapping batches; specialists carrying findings forward across session restarts; product decisions compounding over many review rounds. This requires agents to share, evaluate, and combine each other's cognitive state in real time across sessions. We call this cross-session agent-to-agent cognitive collaboration, distinct from parallel agent execution. To enable it, three problems must be solved together. (P1) Each agent decides field by field what to accept from peers, not accept or reject whole messages. (P2) Every claim is traceable to source, so returning claims are recognised as echoes of the receiver's own prior thinking. (P3) Memory that survives session restarts is relevant because of how it was stored, not how it is retrieved. These are protocol-level properties at the semantic layer of agent communication, distinct from tool-access and task-delegation protocols at lower layers. We call this missing protocol layer "semantic infrastructure," and the Mesh Memory Protocol (MMP) specifies it. Four composable primitives work together: CAT7, a fixed seven-field schema for every Cognitive Memory Block (CMB); SVAF, which evaluates each field against the receiver's role-indexed anchors and realises P1; inter-agent lineage, carried as parents and ancestors of content-hash keys and realising P2; and remix, which stores only the receiver's own role-evaluated understanding of each accepted CMB, never the raw peer signal, realising P3. MMP is specified, shipped, and running in production across three reference deployments, where each session runs an autonomous agent as a mesh peer with its own identity and memory, collaborating with other agents across the network for collective intelligence.

Hongwei Xu

LLM Agent MemoryMulti-Agent CommunicationAgent Memory Management
AskPDF
Apr 20, 2026

HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents

Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer stage with irrelevant context. However, existing memory systems, including hierarchical ones, still often rely solely on vector similarity for retrieval. It tends to produce bloated evidence sets: adding many superficially similar dialogue turns yields little additional recall, but lowers retrieval precision, increases answer-stage context cost, and makes retrieved memories harder to inspect and manage. To address this, we propose HiGMem (Hierarchical and LLM-Guided Memory System), a two-level event-turn memory system that allows LLMs to use event summaries as semantic anchors to predict which related turns are worth reading. This allows the model to inspect high-level event summaries first and then focus on a smaller set of potentially useful turns, providing a concise and reliable evidence set through reasoning, while avoiding the retrieval overhead that would be excessively high compared to vector retrieval. On the LoCoMo10 benchmark, HiGMem achieves the best F1 on four of five question categories and improves adversarial F1 from 0.54 to 0.78 over A-Mem, while retrieving an order of magnitude fewer turns. Code is publicly available at https://github.com/ZeroLoss-Lab/HiGMem.

Shuqi Cao, Jingyi He, Fei Tan

East China Normal University, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China

Persistent Memory for Language ModelsHierarchical MemoryLong-Term Conversational MemoryAgent Memory Management
AskPDF
Apr 20, 2026

A Control Architecture for Training-Free Memory Use

Prompt-injected memory can improve reasoning without updating model weights, but it also creates a control problem: retrieved content helps only when it is applied in the right state. We study this problem in a strict training-free setting and formulate it as applicability control: when to trigger a memory-assisted second pass, when to trust it, and how to maintain the memory bank over time. Our method combines uncertainty-based routing, confidence-based selective acceptance, bank selection across rule and exemplar memory, and evidence-based governance of the memory bank over time. Under a locked training-free protocol with compute-matched controls, it improves two core arithmetic benchmarks by +7.0 points on SVAMP and +7.67 points on ASDiv over baseline. The same architecture also transfers to QA and agent benchmarks with smaller positive effects and shows the same positive direction on a second checkpoint for the main arithmetic tasks. On arithmetic, the main empirical pattern is that the control architecture, rather than raw memory exposure, drives the improvements on SVAMP and ASDiv. Mechanistically, confidence separates helpful from harmful rule-bank interventions, and under fixed retrieval the repair-versus-corrupt difference localizes to rows whose retrieved set actually contains the edited entries.

Yanzhen Lu, Muchen Jiang, Zhicheng Qian +1

Shanghai Qizhi Institute · Nanjing Whale Cloud · Southeast University +1

Memory-Augmented Language ModelsAgent Memory Management
AskPDF
Apr 17, 2026

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents

As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical bottleneck. Agent memory systems and agent skill discovery both address this challenge, extracting reusable knowledge from interaction traces, yet a citation analysis of 1{,}136 references across 22 primary papers reveals a cross-community citation rate below 1%. We propose the Experience Compression Spectrum, a unifying framework that positions memory, skills, and rules as points along a single axis of increasing compression (5--20×\times for episodic memory, 50--500×\times for procedural skills, 1{,}000×\times+ for declarative rules), directly reducing context consumption, retrieval latency, and compute overhead. Mapping 20+ systems onto this spectrum reveals that every system operates at a fixed, predetermined compression level: none supports adaptive cross-level compression, a gap we term the missing diagonal. We further show that specialization alone is insufficient (both communities independently solve shared sub-problems without exchanging solutions), that evaluation methods are tightly coupled to compression levels, that transferability increases with compression at the cost of specificity, and that knowledge lifecycle management remains largely neglected. We articulate open problems and design principles for scalable, full-spectrum agent learning systems.

Xing Zhang, Guanghui Wang, Yanwei Cui +4

AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China.

LLM Agent MemoryLLM Agent Skill LearningLong-Horizon LLM AgentsAgent Memory Management
AskPDF
Apr 17, 2026

A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle

The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, characterized by three properties: persistence, statefulness, and propagation. To systematically characterize this landscape, we propose a Memory Lifecycle Framework that organizes attacks, defenses, and their cross-phase dependencies along two axes: six lifecycle phases (Write, Store, Retrieve, Execute, Share & Propagate, Forget & Rollback) and four security objectives (Integrity, Confidentiality, Availability, Governance). This analysis in turn exposes the need for explicit security requirements at the system level, motivating Verifiable Memory Governance (VMG), a framework of five architectural primitives for specifying and evaluating auditable, recoverable control over memory state within declared system and threat-model boundaries. Our analysis motivates integrating provenance, versioning, and policy-aware retention with retrieval and execution defenses to support auditable prevention, containment, and recovery across the lifecycle.

Zehao Lin, Xixuan Hao, Renyu Fu +5

MemTensor (Shanghai) Technology Co., Ltd. · The Hong Kong University of Science and Technology (Guangzhou) · Shanghai Jiao Tong University

LLM Agent SecurityAI Agent GovernanceAgent Memory Management
AskPDF
Apr 14, 2026

GAM: Hierarchical Graph-based Agentic Memory for LLM Agents

To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient noise. Conversely, discrete structured memory architectures provide robust knowledge retention but often struggle to adapt to evolving narratives. To address this, we propose GAM, a hierarchical Graph-based Agentic Memory framework that explicitly decouples memory encoding from consolidation to effectively resolve the conflict between rapid context perception and stable knowledge retention. By isolating ongoing dialogue in an event progression graph and integrating it into a topic associative network only upon semantic shifts, our approach minimizes interference while preserving long-term consistency. Additionally, we introduce a graph-guided, multi-factor retrieval strategy to enhance context precision. Experiments on LoCoMo and LongDialQA indicate that our method consistently outperforms state-of-the-art baselines in both reasoning accuracy and efficiency.

Zhaofen Wu, Hanrong Zhang, Fulin Lin +9

Zhejiang University · University of Illinois Chicago · Rutgers University +2

Agent Memory ManagementGraph-Based Agent MemoryLong-Term Conversational MemoryMemory-Augmented Language Model Agents
AskPDF
Apr 13, 2026

Memory as Metabolism: A Design for Companion Knowledge Systems

Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM Wiki v2 that compile knowledge into an interlinked artifact for long-term use by a single user. They sit alongside production memory systems that the major labs have shipped for over a year, and an active academic lineage including MemGPT, Generative Agents, Mem0, Zep, A-Mem, MemMachine, SleepGate, and Second Me. Within a 2026 landscape of emerging governance frameworks for agent context and memory -- including Context Cartography and MemOS -- this paper proposes a companion-specific governance profile: a set of normative obligations, a time-structured procedural rule, and testable conformance invariants for the specific failure mode of entrenchment under user-coupled drift in single-user knowledge wikis built on the LLM wiki pattern. The design principle is that personal LLM memory is a companion system: its job is to mirror the user on operational dimensions (working vocabulary, load-bearing structure, continuity of context) and compensate on epistemic failure modes (entrenchment, suppression of contradicting evidence, Kuhnian ossification). Five operations implement this split -- TRIAGE, DECAY, CONTEXTUALIZE, CONSOLIDATE, AUDIT -- supported by memory gravity and minority-hypothesis retention. The sharpest prediction: accumulated contradictory evidence should have a structural path to updating a centrality-protected dominant interpretation through multi-cycle buffer pressure accumulation, a failure mode no existing benchmark captures. The safety story at the single-agent level is partial, and the paper is explicit about what it does and does not solve.

Stefan Miteski

CODE University Berlin

LLM MemoryAgent Memory ManagementAI Agent Governance
AskPDF
Apr 13, 2026

When to Forget: A Memory Governance Primitive

Agent memory systems accumulate experience but currently lack a principled operational metric for memory quality governance -- deciding which memories to trust, suppress, or deprecate as the agent's task distribution shifts. Write-time importance scores are static; dynamic management systems use LLM judgment or structural heuristics rather than outcome feedback. This paper proposes Memory Worth (MW): a two-counter per-memory signal that tracks how often a memory co-occurs with successful versus failed outcomes, providing a lightweight, theoretically grounded foundation for staleness detection, retrieval suppression, and deprecation decisions. We prove that MW converges almost surely to the conditional success probability p+(m) = Pr[y_t = +1 | m in M_t] -- the probability of task success given that memory m is retrieved -- under a stationary retrieval regime with a minimum exploration condition. Importantly, p+(m) is an associational quantity, not a causal one: it measures outcome co-occurrence rather than causal contribution. We argue this is still a useful operational signal for memory governance, and we validate it empirically in a controlled synthetic environment where ground-truth utility is known: after 10,000 episodes, the Spearman rank-correlation between Memory Worth and true utilities reaches rho = 0.89 +/- 0.02 across 20 independent seeds, compared to rho = 0.00 for systems that never update their assessments. A retrieval-realistic micro-experiment with real text and neural embedding retrieval (all-MiniLM-L6-v2) further shows stale memories crossing the low-value threshold (MW = 0.17) while specialist memories remain high-value (MW = 0.77) across 3,000 episodes. The estimator requires only two scalar counters per memory unit and can be added to architectures that already log retrievals and episode outcomes.

Baris Simsek

Agent Memory GovernanceAgent MemoryAgent Memory Management
AskPDF
Apr 13, 2026

The Missing Knowledge Layer in Cognitive Architectures for AI Agents

The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own persistence semantics. This gap produces a category error: systems apply cognitive decay to factual claims, or treat facts and experiences with identical update mechanics. We survey persistence semantics across existing memory systems and identify eight convergence points, from Karpathy's LLM Knowledge Base [10] to the BEAM benchmark's near-zero contradiction-resolution scores [22], all pointing to related architectural gaps. We propose a four-layer decom position (Knowledge, Memory, Wisdom, Intelligence) where each layer has fundamentally different persistence semantics: indefinite supersession, Ebbinghaus decay, evidence-gated revision, and ephemeral inference respectively. Companion implementations in Python and Rust demonstrate the architectural separation is feasible. We borrow terminology from cognitive science as a useful analogy (the Knowledge/Memory distinction echoes Tulving's trichotomy), but our layers are engineering constructs justified by persistence-semantics requirements, not by neural architecture. We argue that these distinctions demand distinct persistence semantics in engineering implementations, and that no current framework or system provides this.

Michaël Roynard

Independant Researcher

Cognitive Architectures for AI AgentsAgent MemoryAgent Memory ManagementKnowledge Representation
AskPDF
Apr 11, 2026

ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents

Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and destructive writeback. We present ClawVM, a virtual memory layer that manages state as typed pages with minimum-fidelity invariants, multi-resolution representations under a token budget, and validated writeback at every lifecycle boundary. Because the harness already assembles prompts, mediates tools, and observes lifecycle events, it is the natural enforcement point; placing the contract there makes residency and durability deterministic and auditable. Across synthetic workloads, 12 real-session traces, and adversarial stress tests, ClawVM eliminates all policy-controllable faults whenever the minimum-fidelity set fits within the token budget, confirmed by an offline oracle, and adds median <50 microseconds of policy-engine overhead per turn.

Mofasshara Rafique, Laurent Bindschaedler

Independent Researcher Switzerland · Max Planck Institute for Software Systems Saarbrücken, Saarland, Germany

LLM Context ManagementAgent Memory ManagementLLM Agent HarnessesRuntime Enforcement for AI Agents
AskPDF
Apr 10, 2026

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding

Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this issue, we propose StreamMeCo, an efficient Stream Agent Memory Compression framework. Specifically, based on the connectivity of the memory graph, StreamMeCo introduces edge-free minmax sampling for the isolated nodes and an edge-aware weight pruning for connected nodes, evicting the redundant memory nodes while maintaining the accuracy. In addition, we introduce a time-decay memory retrieval mechanism to further eliminate the performance degradation caused by memory compression. Extensive experiments on three challenging benchmark datasets (M3-Bench-robot, M3-Bench-web and Video-MME-Long) demonstrate that under 70% memory graph compression, StreamMeCo achieves a 1.87* speedup in memory retrieval while delivering an average accuracy improvement of 1.0%. Our code is available at https://github.com/Celina-love-sweet/StreamMeCo.

Junxi Wang, Te Sun, Jiayi Zhu +6

Shanghai Jiao Tong University · Fudan University · Shanghai AI Laboratory +2

Agent Memory ManagementMemory-Augmented Video UnderstandingStreaming Video UnderstandingGraph-Based Agent Memory
AskPDF
Apr 10, 2026

M⋆^\star: Every Task Deserves Its Own Memory Harness

Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures typically adopt a fixed memory design tailored to specific domains, such as semantic retrieval for conversations or skills reused for coding. However, a memory system optimized for one purpose frequently fails to transfer to others. To address this limitation, we introduce M⋆^\star, a method that automatically discovers task-optimized memory harnesses through executable program evolution. Specifically, M⋆^\star models an agent memory system as a memory program written in Python. This program encapsulates the data Schema, the storage Logic, and the agent workflow Instructions. We optimize these components jointly using a reflective code evolution method; this approach employs a population-based search strategy and analyzes evaluation failures to iteratively refine the candidate programs. We evaluate M⋆^\star on four distinct benchmarks spanning conversation, embodied planning, and expert reasoning. Our results demonstrate that M⋆^\star improves performance over existing fixed-memory baselines robustly across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each domain. This finding indicates that specializing the memory mechanism for a given task explores a broad design space and provides a superior solution compared to general-purpose memory paradigms.

Wenbo Pan, Shujie Liu, Xiangyang Zhou +4

City University of Hong Kong · Microsoft

Agent MemoryAgent Memory ManagementMemory-Augmented Language Model AgentsAgent Harness Optimization
AskPDF
Apr 9, 2026

MemReader: From Passive to Active Extraction for Long-Term Agent Memory

Long-term memory is fundamental for personalized and autonomous agents, yet populating it remains a bottleneck. Existing systems treat memory extraction as a one-shot, passive transcription from context to structured entries, which struggles with noisy dialogue, missing references, and cross-turn dependencies, leading to memory pollution, low-value writes, and inconsistency. In this paper, we introduce the MemReader family for active long-term memory extraction in agent systems: MemReader-0.6B, a compact and cost-efficient passive extractor distilled for accurate and schema-consistent structured outputs, and MemReader-4B, an active extractor optimized with Group Relative Policy Optimization (GRPO) to make memory writing decisions. Under a ReAct-style paradigm, MemReader-4B explicitly evaluates information value, reference ambiguity, and completeness before acting, and can selectively write memories, defer incomplete inputs, retrieve historical context, or discard irrelevant chatter. Experiments on LOCOMO, LongMemEval, and HaluMem show that MemReader consistently outperforms existing extraction-based baselines. In particular, MemReader-4B achieves state-of-the-art performance on tasks involving knowledge updating, temporal reasoning, and hallucination reduction. These results suggest that effective agent memory requires not merely extracting more information, but performing reasoning-driven and selective memory extraction to build low-noise and dynamically evolving long-term memory. Furthermore, MemReader has been integrated into MemOS and is being deployed in real-world applications. To support future research and adoption, we release the models and provide public API access.

Jingyi Kang, Chunyu Li, Ding Chen +3

MemTensor (Shanghai) Technology · China Telecom Research Institute

LLM Agent MemoryAgent Memory Management
AskPDF
Apr 9, 2026

Lightweight LLM Agent Memory with Small Language Models

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low online overhead but suffer from unstable accuracy due to limited query construction and candidate filtering. In contrast, many systems use repeated large-model calls for online memory operations, improving accuracy but accumulating latency over long interactions. We propose LightMem, a lightweight memory system for better agent memory driven by Small Language Models (SLMs). LightMem modularizes memory retrieval, writing, and long-term consolidation, and separates online processing from offline consolidation to enable efficient memory invocation under bounded compute. We organize memory into short-term memory (STM) for immediate conversational context, mid-term memory (MTM) for reusable interaction summaries, and long-term memory (LTM) for consolidated knowledge, and uses user identifiers to support independent retrieval and incremental maintenance in multi-user settings. Online, LightMem operates under a fixed retrieval budget and selects memories via a two-stage procedure: vector-based coarse retrieval followed by semantic consistency re-ranking. Offline, it abstracts reusable interaction evidence and incrementally integrates it into LTM. Experiments show consistent gains across model scales, with an average F1 improvement of about 2.5 over A-MEM on LoCoMo, while achieving higher efficiency and low median latency (83 ms for retrieval and 581 ms end-to-end).

Jiaquan Zhang, Chaoning Zhang, Shuxu Chen +9

University of Electronic Science and Technology of China · Kyung Hee University · City University of Hong Kong +1

Memory Management for LLM AgentsPersistent Memory for Language ModelsAgent Memory ManagementLong-Term Conversational MemoryMemory Consolidation for LLM Agents
AskPDF
Apr 8, 2026

Prism: An Evolutionary Memory Substrate for Multi-Agent Open-Ended Discovery

We introduce \prism{} (Probabilistic Retrieval with Information-Stratified Memory), an evolutionary memory substrate for multi-agent AI systems engaged in open-ended discovery. \prism{} unifies four independently developed paradigms -- layered file-based persistence, vector-augmented semantic memory, graph-structured relational memory, and multi-agent evolutionary search -- under a single decision-theoretic framework with eight interconnected subsystems. We make five contributions: (1)~an entropy-gated stratification mechanism that assigns memories to a tri-partite hub (skills/notes/attempts) based on Shannon information content, with formal context-window utilization bounds; (2)~a causal memory graph G=(V,Er,Ec)\mathcal{G} = (V, E_r, E_c) with interventional edges and agent-attributed provenance; (3)~a Value-of-Information retrieval policy with self-evolving strategy selection; (4)~a heartbeat-driven consolidation controller with stagnation detection via optimal stopping theory; and (5)~a replicator-decay dynamics framework that interprets memory confidence as evolutionary fitness, proving convergence to an Evolutionary Stable Memory Set (ESMS). On the LOCOMO benchmark, \prism{} achieves 88.1 LLM-as-a-Judge score (31.2% over Mem0). On CORAL-style evolutionary optimization tasks, 4-agent \prism{} achieves 2.8×\times higher improvement rate than single-agent baselines.%

Suyash Mishra

AI Researcher · Basel, Switzerland

Agent Memory ManagementGraph-Based Agent MemoryShared-Memory Multi-Agent SystemsAI Agents for Scientific DiscoverySelf-Evolving Agents
AskPDF
Apr 6, 2026

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Coworking AI agents operating within local file systems are rapidly emerging as a paradigm in human-AI interaction; however, effective personalization remains limited by severe data constraints, as strict privacy barriers and the difficulty of jointly collecting multimodal real-world traces prevent scalable training and evaluation, and existing methods remain interaction-centric while overlooking dense behavioral traces in file-system operations; to address this gap, we propose FileGram, a comprehensive framework that grounds agent memory and personalization in file-system behavioral traces, comprising three core components: (1) FileGramEngine, a scalable persona-driven data engine that simulates realistic workflows and generates fine-grained multimodal action sequences at scale; (2) FileGramBench, a diagnostic benchmark grounded in file-system behavioral traces for evaluating memory systems on profile reconstruction, trace disentanglement, persona drift detection, and multimodal grounding; and (3) FileGramOS, a bottom-up memory architecture that builds user profiles directly from atomic actions and content deltas rather than dialogue summaries, encoding these traces into procedural, semantic, and episodic channels with query-time abstraction; extensive experiments show that FileGramBench remains challenging for state-of-the-art memory systems and that FileGramEngine and FileGramOS are effective, and by open-sourcing the framework, we hope to support future research on personalized memory-centric file-system agents.

Shuai Liu, Shulin Tian, Kairui Hu +6

S-Lab, Nanyang Technological University · Synvo AI

Agent MemoryPersonal AI AgentsAgent Memory ManagementMemory Agent BenchmarksSynthetic Data Generation
AskPDF