Peak Memory

Follow this topic Ask about this topic

Momentum

54 papers in the last four weeks, up 157% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 279

May 5, 2026cs.OS

ipc_shared_ptr: A Publish/Subscribe-Aware Smart Pointer for Cross-Process Object Lifetime Management

True zero-copy Inter-Process Communication (IPC) in publish/subscribe (pub/sub) middleware such as Robot Operating System 2 (ROS 2) requires subscribers to reference message objects in publisher-owned shared memory. Objects must not be reclaimed while referenced, yet must eventually be reclaimed, with correct handling of crash recovery and Transient Local QoS retention requirements. We propose ipc_shared_ptr, a pub/sub-aware smart pointer for cross-process message lifetime management. ipc_shared_ptr exploits pub/sub structural properties to specialize Birrell's reference listing, limiting global metadata updates to per-subscriber 0<->1 transitions and achieving an order-of-magnitude reduction in global communication over general-purpose distributed reference counting. We analyze the key metadata management tradeoff: scalability versus implementation simplicity. Owner-driven reclaim offers greater scalability, but concurrent membership changes and reclamation decisions produce races that widen the correctness-verification state space. Single-writer achieves structural atomicity, eliminating this complexity at the cost of a centralized bottleneck. iceoryx2 (owner-driven reclaim) and Agnocast -- a true zero-copy ROS 2 IPC middleware sharing the publisher's heap with subscribers and adopting ipc_shared_ptr with single-writer -- embody each architecture. Comparative evaluation at the scale of Autoware -- the largest open-source ROS 2 application -- confirms that single-writer achieves sufficient scalability: at 200 topics, two subscribers per topic and 100 Hz, Agnocast's E2E p99.9 is 2.9x lower than iceoryx2's, justifying implementation simplicity over owner-driven reclaim.

Takahiro Ishikawa-Aso, Atsushi Yano, Koichi Imai +2

The University of Tokyo, Japan · Saitama University, Japan · TIER IV Incorporated, Japan

Robot Operating System Shared Control Peak Memory Protocol Reactive Journal

May 5, 2026cs.AI

MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents

Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file memory systems. We present MEMTIER, a tripartite memory architecture for the OpenClaw agent runtime that introduces a structured episodic JSONL store, a five-signal weighted retrieval engine, an attention-attributed cognitive weight update loop, an asynchronous consolidation daemon promoting episodic facts to a semantic tier, and a PPO-based policy framework for adapting retrieval weights (infrastructure validated; performance gains pending camera-ready). On the full 500-question LongMemEval-S benchmark (Wu et al., 2025), MEMTIER achieves Acc=0.382, F1=0.412 with Qwen2.5-7B on a consumer 6GB GPU - a +33 percentage point improvement over the full-context baseline (0.050 -> 0.382, i.e., 5% -> 38%). With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG BM25 GPT-4o baseline (0.560) on those categories. Temporal reasoning rises to 0.323 and multi-session synthesis to 0.173, demonstrating that structured semantic pre-population qualitatively changes what lightweight retrieval can achieve. All phases run locally on a consumer laptop with a 6GB GPU.

Bronislav Sidik, Lior Rokach

Institute for Applied AI Research · Faculty of Computer and Information Science · Ben-Gurion University of the Negev, Beer Sheva, Israel

Long-Term Agent Memory Peak Memory Episodic Memory Concept Bottleneck Models

May 5, 2026cs.LG

CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning

To mitigate the memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, rely on low-rank updates. However, such updates fail to fully capture the rank characteristics of the weight modifications observed in full-parameter fine-tuning, resulting in a performance gap. Furthermore, LoRA and other existing PEFT methods still require substantial memory to store the full set of frozen weights, limiting their efficiency in resource-constrained settings. To addres these limitations, we introduce Cumulative Energy-Retaining Subspace Adaptation (CERSA), a novel fine-tuning paradigm that leverages singular value decomposition (SVD) to retain only the principal components responsible for 90% to 95% of the spectral energy. By fine-tuning low-rank representations derived from this principal subspace, CERSA significantly reduces memory consumption. We conduct extensive evaluations of CERSA across models of varying scales and domains, including image recognition, text-to-image generation, and natural language understanding. Empirical results demonstrate that CERSA consistently outperforms state-of-the-art PEFT methods while achieving substantially lower memory requirements. The code will be publicly released.

Jingze Ge, Xue Geng, Yun Liu +6

National University of Singapore · Institute for Infocomm Research (I2R), A*STAR · Nankai University +1

Parameter-Efficient Fine-Tuning Methods Pretraining Subspace Peak Memory Accumulation

May 5, 2026physics.optics

OptiLookUp: An Optical ROM-Based Lookup Table Engine for Photonic Accelerators

Read-only memory (ROM) provides deterministic access to predefined data mappings. Extending ROM concepts to the optical domain enables high-bandwidth, low-latency, and parallel memory access, but realizing compact and reconfigurable optical ROM remains challenging due to loss, wavelength control, and integration constraints. This work presents a high-speed, reconfigurable photonic ROM architecture implemented using integrated microring resonators (MRRs). The ROM encodes predefined input-output mappings directly in the spectral response of the photonic devices, enabling deterministic lookup-based operation without dynamic computation during readout. To improve scalability and reduce cumulative insertion loss, the architecture employs compact banked sub-arrays that are selectively addressed through an optical decoding mechanism. Reconfigurability is achieved using transistor-based optical selectors, allowing different ROM banks to be activated without physical light rerouting or interferometric structures. The proposed photonic ROM is designed and evaluated using device-level simulations based on the GlobalFoundries 45SPCLO silicon photonics platform. Simulation results demonstrate reliable operation at data rates up to 12.5 GHz, with stable light-to-current transfer characteristics obtained through integrated photodiode readout. The optical ROM can be used to implement nonlinear activation functions utilised in photonic accelerator architectures, including sigmoid, tanh, ReLU, and exponential mappings.

Ankur Singh, Akhilesh Jaiswal

Department of Electrical and Computer Engineering, University of Wisconsin–Madison, Madison, WI, USA

Photonic Transformer Accelerators Peak Memory

May 4, 2026cs.CR

Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory

As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives improbable in single-turn settings. Such long-horizon threats pose significant risks to the safe deployment of LLM agents in critical domains. In this paper, we present ShadowMem, a novel defensive framework designed to counter a wide range of long-horizon threats. Inspired by the "shadow stack" abstraction in systems security, ShadowMem maintains a dedicated, safety-focused agentic memory that distills and retains safety-critical context across the agent's full execution trajectory, leveraging this shadow memory to proactively assess the risk of pending actions prior to their execution. Extensive evaluation demonstrates that ShadowMem substantially outperforms existing defenses across diverse long-horizon threats in detection accuracy, achieves early-stage detection for the majority of attacks, and introduces only negligible overhead to agent utility. To our best knowledge, ShadowMem represents the first framework to detect and mitigate long-horizon threats using an agentic memory approach, establishing a new paradigm for this critical challenge and opening promising directions for future research. The artifacts are available at https://github.com/ZJUWYH/ShadowMem

Yuhui Wang, Tanqiu Jiang, Jiacheng Liang +2

Stony Brook University USA · Cisco Systems USA

Multi-Llm Agents Large Language Model Agents Agentic Memory LLM Defense Mechanisms Peak Memory

May 2, 2026cs.CL

MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents

Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenance tracking, and uniform retrieval that ignores query context. We introduce MemORAI (Memory Organization and Retrieval via Adaptive Graph Intelligence), a framework that integrates three innovations: selective memory filtering with dual-layer compression to retain user-persona-relevant content, a provenance-enriched multi-relational graph tracking factual origins at the turn level, and query-adaptive subgraph retrieval with Dynamic Weighted PageRank that applies query-conditioned edge weighting. Evaluated on LOCOMO and LongMemEval benchmarks, MemORAI achieves state-of-the-art performance in memory retrieval and personalized response generation, demonstrating that selective storage, enriched representation, and adaptive retrieval are essential for coherent, personalized LLM agents.

Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan +4

1Independent Researcher · 2Hanoi University of Science and Technology · 3VNU University of Engineering and Technology +1

Graph-Structured Memories Peak Memory Intelligence

May 2, 2026cs.CV

Visual Implicit Autoregressive Modeling

Visual Autoregressive Modeling (VAR) based on next-scale prediction achieves strong generation quality, but their explicit deep stacks fix the amount of computation per scale and inflate memory at high resolutions. We introduce Visual Implicit Autoregressive Modeling (VIAR), a next-scale autoregressive generator that embeds an implicit equilibrium layer between shallow pre/post blocks. The implicit layer is trained with Jacobian-Free Backpropagation, yielding constant training memory, while inference exposes a per-scale iteration knob that enables compute control. On ImageNet 256x256 benchmark, VIAR attains FID 2.16, and sFID 8.07 with only 38.4% parameters of VAR, matching or surpassing strong AR baselines and remaining competitive with large diffusion models. By controlling the per-scale knob, VIAR can reduce peak memory from 19.24 GB to 8.53 GB and doubles throughput from 15.16 to 32.08 images/s on a single RTX 4090, without retraining. Ablations show that fewer steps are sufficient for fixed-point iterations to converge and that VIAR consistently dominates VAR across quality efficiency operating points. In zero shot in-painting and class-conditional editing, VIAR produces sharper details and smoother boundaries while preserving global structure, validating the benefits of implicit equilibria and per-scale compute control for practical, deployable visual generation.

Pengfei Jiang, Jixiang Luo, Luxi Lin +2

Institute of Artificial Intelligence (TeleAI), China Telecom · Xiamen University

Visual Autoregressive Models Autoregressive Image Generation Scaling Peak Memory

May 1, 2026cs.CL

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

Peak Memory Autoregressive Language Models Downstream Fine-Tuning

Apr 30, 2026cs.AI

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

Agentic Memory Semantic Memory Factual Recall Peak Memory Iterative

Apr 30, 2026cs.AI

Contextual Agentic Memory is a Memo, Not True Memory

Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with provable consequences for agent capability, long-term learning, and security. Retrieval generalizes by similarity to stored cases; weight-based memory generalizes by applying abstract rules to inputs never seen before. Conflating the two produces agents that accumulate notes indefinitely without developing expertise, face a provable generalization ceiling on compositionally novel tasks that no increase in context size or retrieval quality can overcome, and are structurally vulnerable to persistent memory poisoning as injected content propagates across all future sessions. Drawing on Complementary Learning Systems theory from neuroscience, we show that biological intelligence solved this problem by pairing fast hippocampal exemplar storage with slow neocortical weight consolidation, and that current AI agents implement only the first half. We formalize these limitations, address four alternative views, and close with a co-existence proposal and a call to action for system builders, benchmark designers, and the memory community.

Binyan Xu, Xilin Dai, Kehuan Zhang

The Chinese University of Hong Kong, Hong Kong, China · Zhejiang University, Hangzhou, China

Agentic Memory Memo Peak Memory Learn Human Visual Cortex

Apr 30, 2026cs.AR

Autoformalizing Memory Specifications with Agents

The primary goal of Design Verification (DV) is to ensure that a proposed chip design implementation (either in code, or physical form) exactly matches its specification and is free of functional errors in order to avoid costly re-designs. Achieving this often demands extensive manual interpretation, translating the specification document into a formal, testable representation. While AI has made progress in DV, current approaches typically focus on narrow, isolated tasks rather than full end-to-end specification compliance of modern chip designs, failing to capture the complexity of real-world verification. Our method automatically formalizes natural language memory chip specifications, for industry relevant Dynamic Random Access Memory (DRAM) standards, into a formal representation called DRAMPyML that can be used for downstream DV tasks like the generation of SystemVerilog assertions, stimulus, and functional coverage. We also release our benchmarking dataset, DRAMBench, which can be used to evaluate the evolution of model capabilities (and new approaches) at hardware autoformalization.

Jan Ole Ernst, Dmitri Michelangelo Saberi, Derek Christ +6

Normal Computing · Fraunhofer Institute for Experimental Software Engineering (IESE), Kaiserslautern, Germany · University of Würzburg, Germany

Chip Design Autoformalization Peak Memory

Apr 29, 2026cs.MA

A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations

Reinforcement Learning (RL) algorithms exhibit high sample complexity, particularly when applied to Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). As a response, projects such as SampleFactory, EnvPool, Brax, and IsaacLab migrate parallel execution of classic environments such as MuJoCo and Atari into C++ thread pools or the GPU to decrease the computational cost of environment steps. We are interested in optimizing the decision-level of human-AI joint operations, so we introduce a compute-efficient Dec-POMDP engine natively architected in C++ called Hide-And-Seek-Engine. By employing Data-Oriented Design (DOD) principles, explicit 64-byte cache-line alignment to remove false sharing, and a zero-copy PyTorch memory bridge using pinned memory and Direct Memory Access (DMA), our engine sustains throughput of up to 33,000,000 steps per second (SPS) in a single-agent, 1024-environment, decentralized observations on an AMD Ryzen 9950X (16 cores). Ten agents reduces FPS to 7M SPS with generating random actions contributing 1/3rd the total runtime for reference. The engine achieves a throughput increase of approximately 3,500

\times

over the baseline single threaded vectorized NumPy implementation and successfully trains cooperative multi-agent policies via PPO, DQN, and SAC in minutes, validating both its performance and generality.

Timothy Flavin, Sandip Sen

Partially Observable Markov Decision Process Single-Agent Peak Memory Human-Ai Collaboration

Apr 28, 2026cs.LG

QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention

FlashAttention improves efficiency through tiling, but its online softmax still relies on floating-point arithmetic for numerical stability, making full quantization difficult. We identify three main obstacles to integer-only FlashAttention: (1) scale explosion during tile-wise accumulation, (2) inefficient shift-based exponential operations on GPUs, and (3) quantization granularity constraints requiring uniform scales for integer comparison. To address these challenges, we propose \textit{QFlash}, an end-to-end integer FlashAttention design that performs softmax entirely in the integer domain and runs as a single Triton kernel. On seven attention workloads from ViT, DeiT, and Swin models, QFlash achieves up to 6.73

\times

speedup over I-ViT and up to 8.69

\times

speedup on Swin, while reducing energy consumption by 18.8% compared to FP16 FlashAttention, without sacrificing Top-1 accuracy on ViT/DeiT and remaining competitive on Swin under per-tensor quantization. Our code is publicly available at https://github.com/EfficientCompLab/qflash.

Sehyeon Oh, Yongin Kwon, Jemin Lee

University of Science and Technology, Daejeon, Republic of Korea · Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea · Pusan National University, Busan, Republic of Korea +1

Block Sparse Flash Attention Quantized Vision Transformer Flash Peak Memory Activation Functions

Apr 26, 2026cs.AI

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\%

vs.

52.2\%

;

91.3\%

) at

1/106^\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=0.05/18

,

p_\text{min}=6.2\times 10^{-31}

,

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 (

ΔQ

up to

-93.7\%

), while moderate conditions mask individual contributions. Sim-Selection sleep adds 37% stability with 47.4% storage reduction (

p \le 5.1\times 10^{-3}

); TripleCopyMemory retains

S(t)=0.912

at 30 days; multi-layer routing beats a flat baseline by

+20.7\%

F1 on LoCoMo,

+19.5\%

on MemoryArena. A cross-provider bias-direction check (

Δ_\text{GPT-Anth}=-0.0001

for ZB vs.

-0.049

for Mem0) rules out LLM-judge-specific confounds. Open-source with 11,589 CI tests.

Alexander Bering

Zensation AI

Peak Memory Artificial Intelligence Systems Raw Judge Outputs

Apr 26, 2026cs.LG

Graph Memory Transformer (GMT)

We investigate whether the Feed-Forward Network (FFN) sublayer in a decoder-only transformer can be replaced by an explicit learned memory graph while preserving the surrounding autoregressive architecture. The proposed Graph Memory Transformer (GMT) keeps causal self-attention intact, but replaces the usual per-token FFN transformation with a memory cell that routes token representations over a learned bank of centroids connected by a learned directed transition matrix. In the base GMT v7 instantiation studied here, each of 16 transformer blocks contains 128 centroids, a 128 * 128 edge matrix, gravitational source routing, token-conditioned target selection, and a gated displacement readout. The cell therefore returns movement from an estimated source memory state toward a target memory state, rather than a retrieved value. The resulting model is a fully decoder-only language model with 82.2M trainable parameters and no dense FFN sublayers, compared with a 103.0M-parameter dense GPT-style baseline used in the evaluation. The base v7 model trains stably and exposes centroid usage, transition structure, and source-to-target movement as directly inspectable quantities of the forward computation. It remains behind the larger dense baseline in validation loss and perplexity (3.5995/36.58 vs. 3.2903/26.85), while showing close zero-shot benchmark behavior under the evaluated setting. These results are not intended as a state-of-the-art claim; they support the viability and structural interpretability of replacing dense within-token transformation with graph-mediated memory navigation. Broader scaling, optimized kernels, and more extensive benchmark evaluation are left for subsequent work.

Nicola Zanarini, Niccolò Ferrari, Evelina Lamma

Bonfiglioli Engineering s.r.l. · Department of Engineering, University of Ferrara, Via Saragat 1, 44122 Ferrara, Italy · NAIS s.r.l., Via Maria Callas 4, 40131 Bologna, Italy

Multiplex Graph Transformers Transformer Encoder Feed-Forward Peak Memory

Apr 24, 2026cs.LG

Score-Repellent Monte Carlo: Toward Efficient Non-Markovian Sampler with Constant Memory in General State Spaces

History-dependent sampling can reduce long-run Monte Carlo variance by discouraging redundant revisits, but existing schemes typically encode history through empirical measure on finite state spaces, which is infeasible in high-dimensional discrete configuration spaces or ill-posed in continuous domains. We propose Score-Repellent Monte Carlo (SRMC) framework that summarizes trajectory history by a running average of score evaluations in

\mathbb{R}^d

, where

d

is the dimension of the score and state representation. This history is converted into a surrogate target through an exponential score tilt, indexed with

α

that represents the strength of repellence in controlling the magnitude of the history-based repulsion. The surrogate family is normalization-free in the standard MCMC sense, yielding a generic wrapper: at each iteration, any base kernel targeting

π

can instead be run on the current surrogate

π_{θ_n}

while the history is updated online. We analyze the coupled evolution of the history recursion and Monte Carlo estimators using stochastic approximation with controlled Markovian noise, establishing almost sure convergence and a joint central limit theorem. We further identify regimes in which the asymptotic covariance decreases as

α

increases, with scaling

O(1/α)

, extending the near-zero-variance effect of finite-state history-dependent samplers to general state spaces with constant memory. Experiments on continuous targets and discrete energy-based models demonstrate improved estimator variance and mode coverage, while retaining

O(d)

memory usage and modest per-iteration overhead.

Jie Hu, Lingyun Chen, Geeho Kim +3

CSE, Oakland University, Rochester, USA · ECE, North Carolina State University, Raleigh, USA · ECE +2

Markovian Sampling Monte Carlo State Space History Peak Memory

Apr 23, 2026cs.DC

Shard the Gradient, Scale the Model: Serverless Federated Aggregation via Gradient Partitioning

Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clients across aggregators, but every aggregator must hold the complete model gradient in memory. When gradients exceed the per-function memory limit (e.g., 10 GB on AWS Lambda), aggregation becomes infeasible regardless of tree depth or branching factor. We propose GradsSharding, which instead partitions the gradient tensor into M shards, each averaged independently by a serverless function that receives contributions from all clients. Because FedAvg averaging is element-wise, this produces bit-identical results to tree-based approaches, so model accuracy is invariant by construction. Per-function memory is bounded at O(|θ|/M), independent of client count, enabling aggregation of arbitrarily large models. We evaluate GradsSharding against lambda-FL and LIFL through HPC experiments and real AWS Lambda deployments across model sizes from 43 MB to 5 GB. Results show a cost crossover at approximately 500 MB gradient size, 2.7x cost reduction at VGG-16 scale, and that GradsSharding is the only architecture that remains deployable beyond the serverless memory ceiling.

Amine Barrak

Department of Computer Science and Engineering, Oakland University, Rochester, MI 48309, USA

Federated Learning Shard Federated Averaging Cloud Partitioning Peak Memory+1

Apr 23, 2026cs.CL

StructMem: Structured Memory for Long-Horizon Behavior in LLMs

Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based memory enables structured reasoning at the cost of expensive and fragile construction. To address these issues, we propose \textbf{StructMem}, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on \texttt{LoCoMo}, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem .

Buqiang Xu, Yijun Chen, Jizhan Fang +5

Zhejiang University · Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph · Ant Group

Graph-Structured Memories Long-Term Memory Peak Memory Temporal Reasoning Relational

Apr 21, 2026cs.MA

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

Multi-Agent Large Language Model Systems Peak Memory Delegation Lineages

Apr 20, 2026cs.AI

WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation

Persistent memory is the bottleneck separating stateless chatbots from long-running agentic systems. Retrieval-augmented generation (RAG) over flat vector stores fragments facts into chunks, loses cross-session identity, and has no first-class notion of supersession or contradiction. Recent bitemporal knowledge-graph systems (Graphiti, Memento, Hydra DB) add typed edges and valid-time metadata, but the graph itself remains flat: no recursive composition, no content-addressed invariants on nodes, and edge types carry no behavior beyond a label. We present WorldDB, a memory engine built on three commitments: (i) every node is a world -- a container with its own interior subgraph, ontology scope, and composed embedding, recursive to arbitrary depth; (ii) nodes are content-addressed and immutable, so any edit produces a new hash at the node and every ancestor, giving a Merkle-style audit trail for free; (iii) edges are write-time programs -- each edge type ships on_insert/on_delete/on_query_rewrite handlers (supersession closes validity, contradicts preserves both sides, same_as stages a merge proposal), so no raw append path exists. On LongMemEval-s (500 questions, ~115k-token conversational stacks), WorldDB with Claude Opus 4.7 as answerer achieves 96.40% overall / 97.11% task-averaged accuracy, a +5.61pp improvement over the previously reported Hydra DB state-of-the-art (90.79%) and +11.20pp over Supermemory (85.20%), with perfect single-session-assistant recall and robust performance on temporal reasoning (96.24%), knowledge update (98.72%), and preference synthesis (96.67%). Ablations show that the engine's graph layer -- resolver-unified entities and typed refers_to edges -- contributes +7.0pp task-averaged independently of the underlying answerer.

Harish Santhanalakshmi Ganesan

Independent Researcher

Temporal Knowledge Graphs Peak Memory Chatbots Vectors

Apr 20, 2026cs.CV

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation

Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory modeling with video generation, leading to inconsistent content during scene revisits and diminished generative capacity when exploring novel regions, even trained on extensive annotated data. To address these limitations, we propose a decoupled framework that separates memory conditioning from generation. Our approach significantly reduces training costs while simultaneously enhancing spatial consistency and preserving the generative capacity for novel scene exploration. Specifically, we employ a lightweight, independent memory branch to learn precise spatial consistency from historical observation. We first introduce a hybrid memory representation to capture complementary temporal and spatial cues from generated frames, then leverage a per-frame cross-attention mechanism to ensure each frame is conditioned exclusively on the most spatially relevant historical information, which is injected into the generative model to ensure spatial consistency. When generating new scenes, a camera-aware gating mechanism is proposed to mediate the interaction between memory and generation modules, enabling memory conditioning only when meaningful historical references exist. Compared with the existing method, our method is highly data-efficient, yet the experiments demonstrate that our approach achieves state-of-the-art performance in terms of both visual quality and spatial consistency.

Yanjun Guo, Zhengqiang Zhang, Pengfei Wang +3

The Hong Kong Polytechnic University · OPPO Research Institute

Video Generation Spatio-Temporal Attention Video Temporal Grounding Cross-Attention Peak Memory Memorization

Apr 18, 2026cs.CL

PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations

As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in high-risk domains. However, existing benchmarks largely rely on mixed queries and posterior evaluation, output-level scoring, which quantifies hallucination severity but offers limited insight into where and why hallucinations arise in the generation pipeline. We therefore reformulate hallucination evaluation as a diagnostic problem and propose PRISM, a controlled benchmark that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors, grounded in three stages of generation (memory, instruction, and reasoning). PRISM contains 9,448 instances across 65 tasks and supports fine-grained, stage-aware diagnostic evaluation. Evaluating 24 mainstream open-source and proprietary LLMs, we uncover consistent trade-offs across instruction following, memory retrieval, and logical reasoning, showing that mitigation strategies often improve specific dimensions at the expense of others. We hope PRISM provides a framework for understanding the specific mechanisms behind LLMs hallucinations, ultimately accelerating the development of trustworthy large language models.

Yuhe Wu, Guangyu Wang, Yuran Chen +6

HKUST(GZ) · NYUSH · DUFE +2

Large Language Model Hallucination Hallucination Detection Reasoning Errors Prism Reasoning Skills Instruction+1

Apr 17, 2026cs.DC

KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving

Power has become a central bottleneck for AI inference. This problem is becoming more urgent as agentic AI emerges as a major workload class, yet prior power-management techniques focus almost entirely on single-turn LLM serving. Our analysis shows that agentic serving behaves fundamentally differently: each request carries long-lived context that evolves across tool-interleaved turns, and lowering GPU frequency can push the system into a thrashing regime where memory pressure sharply worsens both performance and power efficiency. These observations show that power optimization for agentic serving requires rethinking. We present KAIROS, a context-aware power optimization system for agentic AI serving. KAIROS uses agent context as a first-class control signal to jointly manage GPU frequency, per-instance concurrency, and multi-instance request placement. This enables KAIROS to save power when memory headroom exists while avoiding thrashing and preserving performance targets. At a high level, KAIROS tracks requests at agent granularity, adapts local control to context growth and agent progress, and routes agents across instances to jointly improve power efficiency and memory stability. Evaluated across diverse software and data engineering agentic tasks, KAIROS achieves an average of 27% (up to 39.8%) power reduction while meeting the performance targets.

Yichao Yuan, Mosharaf Chowdhury, Nishil Talati

University of Illinois, Urbana Champaign Urbana, IL, USA · University of Michigan Ann Arbor, MI, USA

Agentic Inference Peak Memory Bottlenecks

Apr 17, 2026math.OC

A Wasserstein Geometric Framework for Hebbian Plasticity

We introduce the Tan-HWG framework (Hebbian-Wasserstein-Geometry), a geometric theory of Hebbian plasticity in which memory states are modeled as probability measures evolving through Wasserstein minimizing movements. Hebbian learning rules are formalized as Hebbian energies satisfying a sequential stability condition, ensuring well-posed fiberwise JKO updates, optimal-transport realizations, and an energy descent inequality. This variational structure induces a fundamental separation between internal and observable dynamics. Internal memory states evolve along Wasserstein geodesics in a latent curved space, while observable quantities, such as effective synaptic weights, arise through geometric projection maps into external spaces. Simplicial projections recover classical affine schemes (including exponential moving averages and mirror descent), while revealing synaptic competition and pruning as geometric consequences of mass redistribution. Hilbertian projections provide a geometric account of phase alignment and multi-scale coherence. Classical neural networks appear as flat projections of this curved dynamics, while the framework naturally accommodates richer distributional representations, including structural weights and embedding memories, and their spectral extensions in complex internal spaces. Under mild Lipschitz regularity assumptions, including a quasi-stationary "sleep-mode" regime, we establish the existence of continuous-time limit curves. This yields a variational formulation of memory consolidation as a perturbed Wasserstein gradient flow. The framework thus provides a unified geometric foundation for synaptic plasticity, representation dynamics, and context-dependent computation.

Ulrich Tan

Synaptic Plasticity Plasticity Wasserstein Distance Peak Memory Representation Quality

Apr 17, 2026cs.AI

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 \emph{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 \emph{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.

Large Language Model Agents Long-Term Agent Memory Agent Skill Retrieval Peak Memory Lifecycle Skills+1

Apr 17, 2026cs.LG

PINNACLE: An Open-Source Computational Framework for Classical and Quantum PINNs

We present PINNACLE, an open-source computational framework for physics-informed neural networks (PINNs) that integrates modern training strategies, multi-GPU acceleration, and hybrid quantum-classical architectures within a unified modular workflow. The framework enables systematic evaluation of PINN performance across benchmark problems including 1D hyperbolic conservation laws, incompressible flows, and electromagnetic wave propagation. It supports a range of architectural and training enhancements, including Fourier feature embeddings, random weight factorization, strict boundary condition enforcement, adaptive loss balancing, curriculum training, and second-order optimization strategies, with extensibility to additional methods. We provide a comprehensive benchmark study quantifying the impact of these methods on convergence, accuracy, and computational cost, and analyze distributed data parallel scaling in terms of runtime and memory efficiency. In addition, we extend the framework to hybrid quantum-classical PINNs and derive a formal estimate for circuit-evaluation complexity under parameter-shift differentiation. Results highlight the sensitivity of PINNs to architectural and training choices, confirm their high computational cost relative to classical solvers, and identify regimes where hybrid quantum models offer improved parameter efficiency. PINNACLE provides a foundation for benchmarking physics-informed learning methods and guiding future developments through quantitative assessment of their trade-offs.

Shimon Pisnoy, Hemanth Chandravamsi, Ziv Chen +4

†Faculty of Mechanical Engineering, Technion Israel Institute of Technology, Haifa, Israel. · ‡Corresponding author. · §The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion Israel Institute of Technology, Haifa, Israel. +2

Parametric Physics-Informed Neural Network Peak Memory

Apr 16, 2026cs.AI

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration

While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial memory and inference overhead. Existing approaches such as context compression and multi-token prediction (MTP) improve efficiency from two complementary directions by compressing historical tokens and generating future tokens in parallel. However, effectively combining them remains challenging due to their different training paradigms and architectural assumptions. In this work, we propose MemoSight (Memory-Foresight-Based Reasoning), a unified framework that integrates context compression and MTP to improve inference efficiency while preserving CoT performance. MemoSight adopts a shared minimalist design based on special tokens and token-specific positional layouts for both compression and parallel prediction. Experiments on four reasoning benchmarks show that, compared to the vanilla SFT baseline, MemoSight reduces KV cache usage by up to 66% and improves inference speed by 56%, while incurring less than a 3% drop in average reasoning accuracy, yielding a better efficiency-accuracy trade-off than existing CoT compression methods.

Xinyu Liu, Xin Liu, Bo Jin +8

School of Computer Science and Engineering, Northeastern University, China · Meituan Inc. · NiuTrans Research, Shenyang, China

Multi-Token Prediction Reasoning Benchmark Chain-of-Thought Reasoning Peak Memory Data Compression Methods Acceleration

Apr 9, 2026cs.LG

KV Cache Offloading for Context-Intensive Tasks

With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising approach to reduce memory footprint and inference latency while preserving accuracy. Prior evaluations have largely focused on tasks that do not require extracting large amounts of information from the context. In this work, we study KV-cache offloading on context-intensive tasks: problems where the solution requires looking up a lot of information from the input prompt. We create and release the Text2JSON benchmark, a highly context-intensive task that requires extracting structured knowledge from raw text. We evaluate modern KV offloading on Text2JSON and other context-intensive tasks and find significant performance degradation on both Llama 3 and Qwen 3 models. Our analysis identifies two key reasons for poor accuracy: low-rank projection of keys and unreliable landmarks, and proposes a simpler alternative strategy that significantly improves accuracy across multiple LLM families and benchmarks. These findings highlight the need for a comprehensive and rigorous evaluation of long-context compression techniques.

Andrey Bocharnikov, Ivan Ermakov, Denis Kuznedelev +2

HSE, Yandex · Yandex · Yandex, NSU

Kv-Cache Management Efficient Long-Context Inference LLM Inference Optimization Cache Peak Memory

Apr 8, 2026cs.LG

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8

\times

A800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to

2.8\times

and

2.0\times

in the prefill and decode stages.

Quantong Qiu, Zhiyi Hong, Yi Yang +5

School of Computer Science and Technology, Soochow University · Baidu Inc, China

LLM Inference Optimization Sparsity Peak Memory

Mar 31, 2026cs.CL

APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay

LLM agents rerun full reasoning for every task, even one they solved moments earlier. We introduce \textbf{APEX-EM}, a non-parametric experience memory that stores complete procedural-episodic traces in a typed Procedural Knowledge Graph (PKG) and retrieves them through three channels: semantic search, structural-signature matching over abstract operation sequences, and graph traversal. A Plan-Retrieve-Generate-Iterate-Ingest (PRGII) workflow produces, quality-gates, and commits experiences, indexing both successes and failures so the agent learns what to reuse and what to avoid. No weights change during deployment. We evaluate on five benchmarks: BigCodeBench, KGQAGen-10k, HLE, Lifelong Agent Bench, and ALFWorld. Because prior work uses different backbones, we base our claims on same-backbone comparisons that hold model capability fixed. On held-out BigCodeBench transfer with a shared GPT-4o backbone, APEX-EM gains +7.6,pp over the no-memory baseline,

3.3\times

MemRL's +2.3,pp under the identical setup. On Lifelong Agent Bench with a shared GPT-4o-mini backbone, it gains +1.4,pp (OS) and +1.0,pp (DB) cumulative success. On KGQAGen-10k, frozen memory transfers to a blind 1{,}079-question test split at 73.7% versus 42.0% with no memory, approaching an oracle handed the ground-truth subgraph (84.9%). Across three Opus scales the memory gain stays at +27 to +32,pp, so it adds to model capability rather than substituting for it. Component analysis shows no single mechanism dominates: teacher feedback is negligible for code but adds +10.3,pp on structured queries, structural signatures give

3.3\times

the transfer of semantic-only retrieval, and within-epoch iteration recovers most of the gain when rich feedback is unavailable. These results argue for modular memory composed per domain.

Pratyay Banerjee, Masud Moshtaghi, Ankit Chadha

Amazon, AGI / Sunnyvale, USA

Peak Memory Autonomous Agents Traces Learning-Augmented Algorithms

Mar 10, 2026cs.CR

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Device-side Large Language Models (LLMs) have witnessed explosive growth, offering higher privacy and availability compared to cloud-side LLMs. During LLM inference, both model weights and user data are valuable, and attackers may even compromise the OS kernel to steal them. ARM TrustZone is the de facto hardware-based isolation technology on mobile devices, used to protect sensitive applications from a compromised OS. However, protecting LLM inference with TrustZone incurs significant overhead due to its inflexible isolation of memory and the NPU. To address these challenges, this paper introduces FlexServe, a fast and secure LLM serving system for mobile devices. It first introduces a Flexible Resource Isolation mechanism to construct Flexible Secure Memory (Flex-Mem) and Flexible Secure NPU (Flex-NPU). Both memory pages and the NPU can be efficiently switched between unprotected and protected modes. Based on these mechanisms, FlexServe designs a fast and secure LLM inference framework within TrustZone's secure world. The LLM-Aware Memory Management and Secure Inference Pipeline are introduced to accelerate inference. A Multi-Model Scheduler is proposed to optimize multi-model workflows. We implement a prototype of FlexServe and compare it with two TrustZone-based strawman designs. The results show that FlexServe achieves an average

10.05\times

speedup in Time to First Token (TTFT) compared to the strawman, and an average

2.44\times

TTFT speedup compared to an optimized strawman with pipeline and secure NPU enabled. For multi-model agent workflows, the end-to-end speedup is up to

24.30\times

and

4.05\times

compared to the strawman and optimized strawman, respectively.

Yinpeng Wu, Yitong Chen, Lixiang Wang +3

Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University

LLM Inference Optimization Device Peak Memory

Feb 11, 2026cs.LG

Evaluating Memory Structure in LLM Agents

Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augment reasoning. As researchers create more complex memory architectures, it becomes increasingly difficult to analyze their capabilities and guide future memory designs. Most long-term memory benchmarks focus on simple fact retention, multi-hop recall, and time-based changes. While undoubtedly important, these capabilities can often be achieved with simple retrieval-augmented LLMs and do not test complex memory hierarchies. To bridge this gap, we propose StructMemEval - a benchmark that tests the agent's ability to organize its long-term memory, not just factual recall. We gather a suite of tasks that humans solve by organizing their knowledge in a specific structure: transaction ledgers, to-do lists, trees and others. Our initial experiments show that simple retrieval-augmented LLMs struggle with these tasks, whereas memory agents can reliably solve them if prompted how to organize their memory. However, we also find that modern LLMs do not always recognize the memory structure when not prompted to do so. This highlights an important direction for future improvements in both LLM training and memory frameworks.

Alina Shutova, Alexandra Olenina, Ivan Vinogradov +1

HSE University · Yandex · YSDA +1

Agentic Memory Large Language Model Agents Peak Memory Factual Recall Reusable Knowledge

Jan 9, 2026cs.AI

StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon collaboration due to the lack of memory management, leading to context bloat, error accumulation, and poor cross-task generalization. To address both task-level memory inefficiency and the inability to reuse coordination experience, we propose StackPlanner, a hierarchical multi-agent framework with explicit memory control. StackPlanner addresses these challenges by decoupling high-level coordination from subtask execution with active task-level memory control, and by learning to retrieve and exploit reusable coordination experience via structured experience memory and reinforcement learning. Experiments on multiple deep-search and agent system benchmarks demonstrate the effectiveness of our approach in enabling reliable long-horizon multi-agent collaboration.

Ruizhe Zhang, Xinke Jiang, Zhibang Yang +12

School of Computer Science, Peking University, Beijing, China · 2National Engineering Research Center for Software Engineering, Peking University, Beijing, China · 3Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +5

Global Coordination Planner Agent Agentic Benchmarks Peak Memory

Jan 8, 2026cs.AI

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to memory usage: incorporating all relevant past information can lead to \textit{Memory Anchoring}, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose \textbf{Stee}rable \textbf{M}emory Agent, \texttt{SteeM}, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.

Muzhao Tian, Zisu Huang, Xiaohua Wang +8

College of Computer Science and Artificial Intelligence, Fudan University Shanghai Key Laboratory of Intelligent Information Processing

Interaction History Peak Memory Innovation Prompt Engineering

Dec 31, 2025cs.OS

Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search

Systems resource management tasks rely primarily on hand-designed heuristics. However, growing hardware heterogeneity and workload diversity require heuristics specialized to particular deployment instances, making manual design expensive and difficult to scale. In this paper, we explore how to synthesize systems heuristics using LLMs. The main challenge is ensuring that generated heuristics execute safely, integrate correctly with the surrounding system, and still achieve strong performance. We propose Vulcan, a framework that identifies LLM-friendly interfaces that isolate core decision logic from the rest of the implementation. With Vulcan, LLM-generated code is restricted to simple stateless decision functions, while trusted runtime abstractions provide rich derived statistics for meaningful policy exploration without system-integration bugs. To ensure execution safety, LLMs synthesize heuristics in a restricted language, Anvil, that guarantees important properties by construction. We evaluate Vulcan across three well-studied domains and demonstrate up to 4.9

\times

higher savings for spot-VM scheduling, up to 2

\times

lower miss ratios for cache eviction, and up to 14% higher application performance for tiered-memory systems, while ensuring execution safety throughout.

Rohit Dwivedula, Divyanshu Saxena, Sujay Yadalam +3

The University of Texas at Austin Austin, TX, USA

Large Language Models(Llms Heuristics Schedulers Peak Memory

Jun 2, 2025cs.CL

Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management

FastText remains a practical choice for industrial word representation because it can synthesize vectors for out-of-vocabulary words from character n-grams. Its original hash-bucket implementation, however, couples two engineering compromises that become painful at large scale: unrelated n-grams collide into the same row, while increasing the bucket count quickly turns the input matrix into the dominant memory cost. This paper presents a memory-efficient FastText variant based on an exact-then-compress principle: first give every observed word and n-gram an explicit identity, then compress only those rows whose learned vectors and lexical structure justify sharing. Concretely, we replace hash buckets with collision-free double-array trie indexes and compress the resulting n-gram matrix through structurally constrained prefix and suffix merging followed by mark-compact row reorganization. Unlike arbitrary hashing, the proposed method shares rows only after a high cosine-similarity test, preserving interpretable n-gram identities while reducing the number of live rows. We describe the full training and serving pipeline, including UTF-8 aware n-gram enumeration, double-array trie lookup, memory-mapped model loading, and vector reconstruction for words and sentences. On a large Chinese vocabulary benchmark with 30.1M words and 287.4M extracted n-grams, the compressed model reduces memory from 145.2GB to 28.9GB, improves load time from 12.3 minutes to 3.2 minutes, and preserves downstream quality within 0.3 points of a hash-free model. We position the result as a compact lexical memory layer for LLM-era retrieval systems and release the implementation as an extended FastText prototype.

Yimin Du

Independent Researcher Beijing, China

Unigram Tokenizer Token Embeddings Large Language Model Compression Peak Memory Locality-Sensitive Hashing

Apr 30, 2025cs.IT

Sionna RT: Technical Report

Sionna is an open-source, GPU-accelerated library that, as of version 0.14, incorporates a ray tracer, Sionna RT, for simulating radio wave propagation. A unique feature of Sionna RT is differentiability, enabling the calculation of gradients for the channel impulse responses (CIRs), radio maps, and other related metrics with respect to system and environmental parameters, such as material properties, antenna patterns, and array geometries. The release of Sionna 1.0 provided a complete overhaul of the ray tracer, significantly improving its speed, memory efficiency, and extensibility. This document details the algorithms employed by Sionna RT to simulate radio wave propagation efficiently, while also addressing their current limitations. Given that the computation of CIRs and radio maps requires distinct algorithms, these are detailed in separate sections. For CIRs, Sionna RT integrates shooting and bouncing of rays (SBR) with the image method and uses a hashing-based mechanism to efficiently eliminate duplicate paths. Radio maps are computed using a purely SBR-based approach for the non-diffracted component, complemented by a stage for diffracted paths.

Fayçal Aït Aoudia, Jakob Hoydis, Merlin Nimier-David +3

Radio Map Estimation Raymap-Induced Geometry Technical Report Real-Time Systems Peak Memory

Feb 20, 2025cs.CL

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these tokens -- especially stopwords, articles, and commas -- consistently degrades performance on MMLU and BABILong-4k, even if removing only irrelevant tokens. Our analysis also shows a strong correlation between contextualization and linearity, where linearity measures how closely the transformation from one layer's embeddings to the next can be approximated by a single linear mapping. These findings underscore the hidden importance of filler tokens in maintaining context. For further exploration, we present LLM-Microscope, an open-source toolkit that assesses token-level nonlinearity, evaluates contextual memory, visualizes intermediate layer contributions (via an adapted Logit Lens), and measures the intrinsic dimensionality of representations. This toolkit illuminates how seemingly trivial tokens can be critical for long-range understanding.

Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4

AIRI · Skoltech · Lomonosov Moscow State University +1

Efficient Long-Context Inference Token-Level Uncertainty Transformer Architectures Long-Range Coherence Peak Memory Microscopy

Jun 13, 2021cs.LG

XConv: Low-memory stochastic backpropagation for convolutional layers

Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation. Existing remedies (checkpointing, invertible architectures, or gradient-approximation methods such as randomized automatic differentiation) either add significant computation, impose architectural constraints, or require non-trivial code changes. We propose XConv, a near-drop-in replacement for standard 2D and 3D convolutional layers that addresses all three: it preserves standard backpropagation, imposes no architectural constraints, and integrates into existing codebases with minimal changes. XConv exploits the algebraic structure of convolutional weight gradients, storing highly compressed projections of the activations rather than the full tensors and approximating the gradients via multi-channel randomized trace estimation. The number of probing vectors sets a memory-accuracy tradeoff and recovers the exact gradient in the limit. We establish convergence guarantees and error bounds for the estimator, showing that its gradient-error variance is comparable to that of stochastic gradient descent. Empirically, XConv matches exact-gradient methods across classification, generative modeling, super-resolution, inpainting, and segmentation, with gaps that narrow as the number of probing vectors grows, while reducing activation memory by a factor of two or more when convolutional activations dominate, and remaining computationally competitive with optimized convolution kernels at larger batch sizes. At half precision the gradient-approximation error falls to the rounding floor, so XConv adds essentially no error beyond that of low-precision arithmetic. The savings matter most where activation memory rather than compute is the binding constraint, such as high-resolution and volumetric training and on-device finetuning.

Anirudh Thatipelli, Jeffrey Sam, Mathias Louboutin +3

University of Central Florida · Rice University · DevitoCodes Ltd +2

Convolutional Backpropagation Equivariant Neural Networks Peak Memory Stochastic