Long-Context Modeling

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 83% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 105

Oct 7, 2026cs.LG

Learning infinite context windows in recurrent architectures via spatial neural computing

Recurrent neural networks (RNNs) offer linear-time scaling with sequence length while requiring only constant memory, yet they struggle to capture long-range dependencies due to vanishing gradients and limited receptive fields. To address these limitations, we introduce a second-order recurrent model in which the standard neuron-to-neuron communication is replaced by a spatially evolving field governed by (discretized) partial differential equations. Drawing inspiration from the role of cortical waves in brain computation, this mechanism allows structured spatiotemporal patterns to serve as an implicit, high-capacity memory. We show that the resulting model is equivalent to a structured infinite-order RNN in which the current state depends explicitly on its entire history of past states, yielding an effectively unbounded receptive field with a fixed number of parameters. We further derive constructive conditions to ensure marginal stability, constraining the gradient spectrum on the unit circle and thereby eliminating vanishing and exploding gradients. Empirically, the proposed architecture outperforms other recurrent models on long-horizon benchmarks while using substantially fewer parameters, demonstrating that spatial dynamics can effectively bridge the gap between efficient inference and long-term memory.

Aleix Salvador-Pomarol, Arthur N. Montanari, Earl K. Miller +2

UC San Diego · Northwestern University · Massachusetts Institute of Technology

Recurrent Neural Networks Long-Context Modeling

Oct 6, 2026cs.LG

PHBA: Prefix-State Hybrid Block Attention

Hybrid architectures combining linear sequence models with softmax attention provide an effective balance between efficient long-context modeling and precise token retrieval. Existing designs such as Native Hybrid Attention (NHA) combine compressed long-term states with sliding-window attention, but their exact attention is restricted to a fixed local window. In this work, we introduce Prefix-State Hybrid Block Attention (PHBA), which replaces local sliding-window attention with top-k block-sparse retrieval and couples each retrieved block with a compact prefix state summarizing its preceding context. The prefix states are constructed by a gated linear recurrence at block boundaries and retrieved together with the corresponding token blocks, allowing the model to combine precise long-range evidence with compressed historical context within a unified layer. We further develop a hardware-aware Triton implementation that streams routed token blocks and prefix states without materializing large intermediate tensors. Experiments show that PHBA improves long-context and retrieval performance over strong linear and hybrid baselines while retaining efficient training and inference.

Ruijie Li, Jiaxi Hu, Shiyu Wang +1

The Hong Kong University of Science and Technology (Guangzhou) · Independent researcher

Long-Context Modeling Linear Attention Hybrid Attention Block-Sparse Attention

Oct 6, 2026cs.CL

Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval

Long-term conversational memory is becoming an integral component of modern LLM systems. Proposed architectures group records by topics and events, construct hierarchies and graphs, and connect facts through causal and temporal relations. We experimentally study the interaction between two memory parameters: structural depth and the width of context supplied to the answer model. Using EverMemBench, we evaluate depths D1-D4, core budgets of 1,024/2,048/4,096 tokens, and additional Production and Oracle conditions up to the full archive. Increasing width from 1K to 4K improves Accuracy by 10.11-17.98 percentage points, whereas increasing depth provides no monotonic gain. Beyond 8-16K, Production performance reaches a plateau while tokens per correct answer continue to increase; Oracle preserves quality on full archives of 68-71K tokens. These results motivate further investigation of large, coherent context blocks instead of progressively deeper memory structures.

Michael Andreev

Independent Researcher

Conversational Memory LLM Evaluation Long-Context Modeling Hierarchical Memory Long-Term Conversational Memory

Sep 30, 2026cs.CL

StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning

Large language models deployed as personalized assistants must reason over long, evolving interaction histories. However, in long-term dialogue reasoning, relevant evidence is scattered across sessions, preferences may be revised over time, and standard long-context training fails to address these challenges under data scarcity and prohibitive computational costs. We propose StateTree, a data-driven RL method that constructs a challenging auxiliary task from scarce dialogues with verifiable ground truth. StateTree augments multi-session dialogues with a tree-structured path-tracing task: key-value records are embedded across sessions to form a binary tree. Solving the task requires the model to traverse from root to leaf by retrieving records across sessions and comparing timestamps to resolve branches, then recover the hidden target question among distractor leaves. We apply curriculum RL training progressively increasing tree depth and introduce a compositional variant whose edges carry step-level reasoning fragments, training the model to compose partial cues into coherent queries. Trained on 10K-token contexts, StateTree generalizes to 128K tokens without full-length RL costs and exhibits capabilities including cross-session retrieval, temporal reasoning, knowledge update, and compositional multi-hop reasoning. StateTree outperforms both SFT and RL-based baselines while preserving short-context general reasoning. StateTree-7B achieves gains up to +23.60% on LongMemEval (128k), and StateTree-14B reaches 59.00% accuracy on LongMemEval, surpassing QwenLong-L1-32B (45.20%).

Naen Xu, Wanqing Cui, Yibo Hu +5

Zhejiang University · Taobao & Tmall Group of Alibaba

Temporal Reasoning in Language Models RL for Language Model Reasoning Long-Context Modeling Long-Term Conversational Memory

Sep 29, 2026cs.AI

ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents

Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative agents autonomously perceive external platforms, reason over user preferences, and execute decisions. However, existing RecAgents still suffer from two critical limitations: brittle item perception based on noisy and heterogeneous item pages, and inefficient long-context reasoning over extended user histories and multi-step interaction traces. To address these challenges, we propose a novel recommendation agent framework, termed as ReMem, that combines OCR-based multimodal perception with time-evolving dynamic memory. Instead of parsing raw HTML, ReMem observes item pages through screenshots and extracts structured multimodal information via an OCR tool, enabling a more humanoid and platform-agnostic perception mechanism. To support long-horizon preference modeling, ReMem further introduces a chunk-wise sequential memory update strategy, where the agent selectively maintains a fixed-size memory of informative historical interactions while processing arbitrarily long contexts with linear inference complexity and bounded context length. This design allows the agent to preserve evolving user preferences without relying on external memory modules or disrupting the standard autoregressive generation process. To enhance the dynamic memory instruction, we further develop a multi-memory GRPO variant, which propagates the final-answer advantage to all intermediate conversations that contribute to the final response. Extensive experiments on three datasets demonstrate that ReMem consistently outperforms state-of-the-art baselines, achieving an average improvement of 5.16% across three recommendation agent tasks, namely searching, ranking, and judging.

Haohao Qu, Yongcheng Jing, Chun Hin Chan +3

The Hong Kong Polytechnic University Hong Kong · Nanyang Technological University Singapore

Long-Context Modeling Recommender Systems Large Language Model-Based Recommendation RL for LLM Agents Memory-Augmented Language Model Agents

Sep 28, 2026cs.AI

SMat-Attention: Structured Long-Context Sequence Modeling

Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear attention obtains linear-time training and constant-time decoding by compressing history into a fixed-size state. In this work, we ask whether we can connect these regimes through a tunable notion of structure. To this end, we introduce Structured Matrix Attention (SMat-Attention) via a family of causal masks with structured long-range routing whose row supports have VC-dimension

d

. In our construction,

d=1

recovers the standard causal mask, and increasing

d

permits richer subset-routing patterns. We give chunkwise forward and backward algorithms to enable hardware-efficiency. For sequences of length

T

, the hard-routing construction takes

O(T^{2-3/d}+T)

work, despite the mask being dense, for our prescribed family. In fixed-horizon streaming, decoding after the distant prefix takes constant time per token using

O(T^{1-1/d})

cached states. SMat-Attention therefore makes VC-dimension an explicit knob governing access-pattern complexity, prefill cost, and decoding memory. Empirically, subset-routing and rule-assisted multi-key retrieval experiments illustrate the masks' routing expressiveness. Extensions to Mamba-2 and Gated DeltaNet using learned routing with top-

k

query reads retain subquadratic prefill, improve recall accuracy over the backbones in several settings, and achieve comparable small-scale language-modeling performance.

Emile Anand, Abdullah Ateyeh, Archer Wang +1

Massachusetts Institute of Technology

Long-Context Modeling Linear Attention Attention Mechanisms

Sep 28, 2026cs.LG

Universality and Generalization of Causal Transformers Across Context Lengths

Long contexts are central to modern transformer systems, but most expressivity results choose a different network for each fixed sequence length. We study whether one masked transformer can approximate causal token-to-token maps uniformly over sequences of arbitrary length sampling a fixed normalized horizon. To relate sampling resolutions, we model tokens by

α

-Hölder sequences or, more generally, a common modulus of continuity. Our notion of continuity across resolutions characterizes the causal families admitting uniform approximation on these compact input classes by a single transformer with length-independent parameters. The result extends to the infinite-length mean-field limit, where tokens form continuous curves and masked attention becomes a causal time integral. For bounded regression with target maps satisfying a

β

-smooth stability condition defined using regular test functions, quantitative approximation yields a generalization bound: exact empirical risk minimization over suitably sized bounded-weight transformers gives root mean-square prediction error

O((\log\log N/\log N)^{β/(d+2)})

from

N

iid labeled sequences. The bound holds at fixed confidence on the same sampling distribution, with

d

the token dimension and no maximum-length factor. Finally, experiments on physical time series support the Hölder-regular token model at observed scales, with dataset-dependent fitted exponents, whereas text input embeddings provide a contrasting case. Native and dense sampling, shuffled controls, and refinement checks delimit this empirical regularity regime.

Takashi Furuya, Maarten V. de Hoop, Gabriel Peyré

Doshisha University, RIKEN AIP · Rice University · CNRS, ENS, PSL Université

Neural Network Generalization Transformer Expressivity Length Generalization Long-Context Modeling Time Series Transformers

Sep 24, 2026cs.AI

When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression

Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions have been executed and observed. Unlike static Chain of Thought compression, removing historical reasoning can change future actions and the resulting interaction trajectory. We study when such reasoning can be safely forgotten. We propose Interaction Aware Compression for Long Horizon Reasoning (ICLR), a training free online method that ranks reasoning blocks using frozen proxy entropy while preserving actions, tool calls, and observations. On 260 WorkBuddyBench tasks, ICLR improves average reward from 0.699 to 0.718, while reducing input, output, and cache read tokens by 25.5%, 14.4%, and 33.3%, respectively. Ablations reveal trajectory amplification, where local reasoning deletion produces nonlinear changes in total computation by altering subsequent interaction. Representation probing, activation patching, and controlled trajectory analyses further suggest that historical reasoning becomes more replaceable once task relevant derived state has been reliably externalized into code, files, tool outputs, or environmental feedback. These results characterize agent reasoning as dynamic working state rather than permanent interaction history.

Mingxuan Wang, Fei Luo, Bo Wang +6

TierFlow Team · Gaoling School of Artificial Intelligence, Renmin University of China · Tsinghua University

Long-Context Modeling Long-Horizon LLM Agents CoT Compression Context Compression

Sep 15, 2026cs.LG

On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models

State Space Models (SSMs) have emerged as a compelling alternative to Transformers, enabling sequence modeling with constant memory and linear compute. Although SSMs exhibit reasonable performance and favorable computational characteristics, they continue to lag behind Transformers on tasks that require in-context learning and precise retrieval, slowing their adoption for large-scale language modeling. In this work, we demonstrate that both the success and failure of SSMs in these domains can be explained by studying the role of the gating mechanism, a prevalent component in modern recurrent networks. Specifically, we show through theory and experiments that this gating mechanism causes SSMs to first learn an in-weights "memorization" solution, while delaying, or even preventing, convergence to a correct in-context learning solution. Importantly, this happens even in cases where there are no fundamental limitations due to the architecture or its memory capacity. On the other hand, we find that gating is often beneficial for improving generalization to long sequence lengths. Our results illuminate the crucial role of the gating mechanism in shaping both the training dynamics and generalization of SSMs, and provide a basis for understanding and improving linear-time models.

William L. Tong, Aryo Lotfi, Emmanuel Abbe +6

Harvard University · Apple

Memorization in Language Models Long-Context Modeling In-Context Learning State Space Models

Sep 14, 2026cs.AI

Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size

Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increases proportionally to input length. Although model optimization and lossy prompt compression are widely used, these methods still fail to solve the long-context recall problem beyond pretrained and size-constrained context windows. This paper proposes a long-context recall method that maintains near-constant GPU memory usage as context length increases, without additional training. The main idea is to reconstruct facts using parameter activations in the LLM's feed-forward layers, which store residual vectors representing facts from the source document. Utilizing residual vectors allows the LLM to deterministically reconstruct query relevant facts without referencing the original document, preserving high fidelity and reducing memory usage without fine-tuning weights. Experimental results show that the proposed method enables answering single-fact questions in two-million-token story contexts where previous methods fail.

MyungHoon Ryu, XinYu Piao, Jong-Kook Kim

Korea University South Korea

LLM Memory Long-Context Modeling

Sep 9, 2026cs.AI

ConvMem: Convolutional Memory for Long-Context Reasoning

While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the effective context by reading text in segments and iteratively updating a fixed-size memory. However, this sequential paradigm suffers from high latency and requires costly reinforcement learning (RL) training, which can lead to overfitting on specific datasets. To overcome these limitations, we propose ConvMem, a training-free, highly parallelizable framework that reformulates long-context reasoning as a hierarchical convolution. Inspired by CNNs, ConvMem treats an LLM prompted with a specific query as a convolutional kernel. This kernel summarizes text segments hierarchically, shortening the reasoning path from a linear chain into a logarithmic tree. Specifically, ConvMem integrates \textit{Configurable Strides} and \textit{Skip Connections} to ensure robust evidence capture and propagation, while employing \textit{Multi-Kernel Convolution} to decompose complex queries into disentangled semantic channels. This design not only mitigates error accumulation but also enables massive parallelization across both text segments and reasoning threads. Experiments on RULER-HotpotQA and RULER-2WikiMultiHopQA demonstrate that ConvMem outperforms training-free baselines and avoids the risk of overfitting to parametric priors often observed in RL-trained models on out-of-distribution tasks.

Hongming Zhang, Zhaozhen Gu, Fengshuo Bai +6

Institute of Automation, Chinese Academy of Sciences

Memory-Augmented Language Models Long-Context Modeling

Sep 8, 2026cs.LG

Learning Length-Extrapolatable Recurrent Models

Recurrent models provide a natural path to long-context modeling, yet models trained with backpropagation through time (BPTT) often fail beyond their training horizon. Classical analyses emphasize gradients that vanish or explode along temporal paths. However, dense per-token losses can still train a shared recurrent rule despite severe decay, showing that decay alone does not determine whether learning fails. We instead study state credit: the signal through which future losses reach earlier recurrent states before contributing to parameter updates. Accordingly, we intervene directly on state credit and propose Credit Stabilization through Time (CST). During backward propagation, CST locally rescales the state-credit signal to stabilize its norm without rotating the component being corrected, while leaving the forward computation unchanged. Because controlled synthetic tasks and real data exhibit different credit dynamics, we specialize CST to each regime. In both settings, CST improves performance beyond the training horizon, with gains observed at up to 128x the training length.

Hanwen Jiang

Adobe Research

Backpropagation Temporal Credit Assignment Recurrent Neural Networks Length Generalization Long-Context Modeling

Sep 8, 2026cs.CV

CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling

Long-form instructional videos require automatic chaptering to support browsing, navigation, and knowledge access. Recent long-context language models can perform chaptering from textualized video inputs, but they remain costly and brittle for content-dense lecture videos with long transcripts, smooth topic transitions, and detailed chapter outputs. A scalable segment-then-caption paradigm reduces this cost, but introduces two new challenges: boundary error propagation and fragmented cross-chapter context. We propose \textbf{CausalChapter}, an intervention-inspired framework for long-video chaptering that estimates prediction-level influence through lightweight masking and removal interventions. For boundary localization, our Local Dependency Shift module detects drops in predictive dependency between adjacent temporal windows; for chapter description generation, our Cross-Segment Support Selection module reranks historical contexts according to their support for the current prediction. Experiments on long-video chaptering benchmarks show that CausalChapter improves boundary localization, chapter description quality, and cross-chapter coherence.

Xinran Duan, Guozhang Li, Yaoyao Zhong +3

School of Artificial Intelligence, Beijing Normal University

Long-Context Modeling Long-Video Understanding

Sep 8, 2026cs.IR

SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching

Modeling long-term user behavior is central to sequential recommendation and billion-scale industrial recommender systems, yet production ranking models operate under strict latency, memory, communication, and training-throughput constraints. At the 100K scale, the challenge extends beyond attention complexity: raw sequence features must be stored, transferred, and repeatedly processed during training and online serving. Existing approaches based on history truncation, multi-stage behavior retrieval, compressed lifelong histories, or train-short/infer-long extrapolation either weaken end-to-end optimization or retain substantial length-dependent cost. We present SequenceO1, an end-to-end framework for ultra-long user behavior sequence modeling, deployed at full traffic on Douyin with histories of up to 100K interactions. SequenceO1 follows a compress-then-reason design. Its Sketch Attention (SA) uses learnable prototypes and prototype-wise normalization to compress the raw history into a fixed-size, target-agnostic user representation. Target-conditioned Stacked Target-to-History Cross Attention (STCA) then models complementary time scales: a recent 10K suffix for short-term interests and the compact sketch for long-term preferences. To make training and inference practical, SequenceO1 combines low-rank user representation caching, multi-request user-level batching, pipeline lift, and a fused FlashSA kernel to amortize feature storage, communication, and computation across targets, training instances, and consecutive requests. Production experiments show consistent offline and online gains, while the compact cached sketch retains most of the benefit of directly scaling end-to-end sequence ranking to 100K. These results provide a practical model-system approach to efficient attention, sequence compression, and scalable long-sequence and long-context recommendation systems.

Lin Guan, Jia-Qi Yang, Zhishan Zhao +15

ByteDance

Sequential Recommendation Long-Context Modeling User Preference Modeling

Aug 31, 2026cs.CL

Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention

Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the past. We add to the Kathleen trunk a second memory layer -- a "notebook": a fixed-key holographic (HRR) associative store with a learned local write gate, a self-gating raw read, and write-triggered forgetting -- 25K parameters that attach to the logits of any trunk. (1) Mechanism: on a controlled needle-in-haystack task the notebook reaches 80-82% one-shot recall at 4x the training length, where the bare trunk scores ~4% and a parameter-matched attention head scores 100% inside its training length and 0% beyond it. Addressing is length-invariant by construction; the untrained memory alone recalls at 90% accuracy identically at 512, 2048 and 4096 bytes. Because the store is a linear superposition, two capabilities follow from arithmetic alone: selective unlearning (one subtraction erases one fact to chance, retained facts unharmed) and per-token attribution (counterfactual erasure names the source fact of every correct byte, 100% provenance). (2) Real text: on WikiText-2 bytes the notebook improves prediction of repeated rare words by +0.15-0.27 bits/byte, the gain growing with the distance between mentions and holding zero-shot at 4x training length; write-triggered forgetting eliminates memory pollution at 8x length (first-mention cost +0.33 -> -0.004). (3) Scope and scale: a parameter-matched attention head does generalize on natural-text repetition, so the notebook's claim is exact recall at O(L); on a WikiText-103 ladder (8 to 512 MB) the zero-shot repeat gain rises monotonically. All experiments are pre-registered, seeds reported, and reproducible on a single free-tier GPU.

George Fountzoulas

Department of Computer Engineering & Informatics Frederick University, Nicosia, Cyprus

Memory-Augmented Neural Networks Persistent Memory for Language Models Long-Context Modeling Associative Memory

Aug 30, 2026cs.CL

REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling

Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models reach 32K tokens only through architectural workarounds or by stretching billion-parameter LLMs. We propose REIGN (Refurbished Embeddings with Integrated Guidance Networks), a contrastively trained bi-encoder that operates on sequences of contextualised chunk embeddings from a frozen Guidance Network (GN) rather than on raw tokens. REIGN targets multi-chunk inputs, primarily for document-to-document retrieval; single-chunk inputs stay with the GN. Decoupling token-level processing from document-level reasoning, and caching the GN embeddings to disk, cuts per-document training cost by roughly four orders of magnitude relative to chunked Transformer fine-tuning. We also release a synthetic long-document retrieval benchmark for contrastive training and evaluation at long context lengths. Across an in-distribution Wikipedia benchmark, the LoCo out-of-distribution suite, and a real-world patent retrieval case study, REIGN matches dense long-context retrievers at smaller parameter budgets in each regime. A paired significance test puts it on par with models 1.6-4.3x larger on the patent task, and it stays within 0.65 nDCG@10 of a 20x-larger model on LoCo.

Devrim Çavuşoğlu, Emre Akbaş

Middle East Technical University · OBSS AI

Long-Context Retrieval Long-Context Modeling Text Embedding Models Dense Retrieval

Aug 13, 2026cs.LG

The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning

Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences. It remains unclear whether these choices sacrifice information needed for rhythm inference and longitudinal consistency in real-world ambulatory recordings. We present a controlled study on the Icentia11k single-lead dataset that varies (i) the input horizon (16 seconds, 1 minute, 5 minutes, and 10 minutes) and (ii) the front-end representation (continuous convolutional patch embeddings vs. fixed vector-quantized tokens), while holding the Transformer backbone and training protocol constant. Representations are assessed by downstream abnormal rhythm detection and by patient-level retrieval that probes cross-session stability. Our results show that increasing temporal context beyond 16-second snapshots yields stronger transfer and higher retrieval accuracy, with the strongest performance achieved by the 5- and 10-minute models, indicating improved capture of slow-varying rhythm dynamics and individual-specific structure. Across all evaluated horizons, continuous patch embeddings outperform discretized tokens, suggesting that quantization can discard clinically relevant waveform detail. These findings motivate ECG foundation models that emphasize extended context and continuous encoders for clinical prediction and similarity-based applications. Our code and pretrained models are publicly available at https://github.com/muha-0/ecg-ssl-representation-learning.

Ahmed Sameh, Ramzi Al-Sharawi, Yogatheesan Varatharajah

Computer Science & Engineering, University of Minnesota Twin Cities, Minneapolis, MN 55455. · Robotics, University of Minnesota Twin Cities, Minneapolis, MN 55455.

Self-Supervised Time Series Representation Learning Electrocardiogram Foundation Models Long-Context Modeling Electrocardiogram Classification

Aug 12, 2026cs.LG

MARCH: Scaling Recurrent Memory with Content-Routed State Anchors

Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic computation complexity during training and a key--value cache that grows linearly during autoregressive inference. Recurrent alternatives offer efficient decoding by compressing the entire history into a fixed-size state, but often underperform on recall-intensive tasks since earlier associations usually get overwritten by subsequent updates, and only the most recent contextual information is retained. In this paper, we introduce Memory-Anchor Routing across Context History (MARCH), a network architecture that effectively scales state-space models beyond a fixed-size dimension, while maintaining computational efficiency over long-sequences. MARCH periodically caches cumulative recurrent-state checkpoints as state anchors and associates each anchor with a compact, content-conditioned anchor key. This lets MARCH maintain a memory bank, which can grow as context length increases, providing a controllable trade-off between historical resolution and memory cost. At each token, MARCH produces an anchor query to attend all causally available state anchors, and the output is calculated as an attention-style aggregation over all historical anchors along the current state. We show that after standard pretraining, MARCH consistently outperforms multiple linear attention variants across commonsense reasoning, LongBench, and in-context retrieval. These results demonstrate that content-routed state caching substantially strengthens recurrent long-range memory while preserving its native computation path.

Ming Zhang, Kaisen Yang, Shu Yu +6

Shanghai AI Laboratory · Tsinghua University · Fudan University

Long-Context Retrieval In-Context Retrieval Memory-Augmented Language Models Persistent Memory for Language Models Long-Context Modeling State Space Models

Aug 12, 2026cs.LG

Disentangling the Expressivity of RoPE

Two accounts recur in explanations of the success of rotary position embeddings (RoPE). Expressivity studies associate periodic position information with modular predicates, whereas mechanistic and long-context studies emphasize positional anchors and local offsets. We formalize both accounts for fully uniform, finite-precision soft-attention transformers. We find that, if every rotary component is periodic, RoPE transformers recognize exactly the languages definable in past temporal logic with modular predicates. Conventional RoPE is different: The rotations it computes never repeat. This yields a precision-dependent bounded simulation of fixed-offset look-back operators, rather than an all-length modular characterization. Controlled experiments match this separation: Constructed periodic schedules length-generalize on modular languages, while conventional RoPE behaves more like a bounded locality bias and can impair tasks requiring position-invariant access to distant context. Altogether, our findings shed light on RoPE transformers, bringing theoretical expressivity characterizations closer to models used in practice.

Selim Jerad, Anej Svete, Jiaoda Li +1

Toyota Technological Institute at Chicago · ETH Zürich

Rotary Positional Embeddings Transformer Expressivity Long-Context Modeling

Aug 10, 2026cs.LG

MixFormer: Linear Transformer with Mixture of Memory Experts

State Space Models (SSMs), as a mainstream research direction of linear Transformers, aim to achieve higher efficiency than standard Transformers in long-context modeling. However, existing SSMs suffer from limited input adaptivity and constrained memory capacity, leading to information loss when modeling ultra-long sequences. To address these limitations, we propose MixFormer, a novel linear Transformer that integrates a Mixture-of-Memory-Experts (MoE) mechanism. Specifically, the model maintains differentiated memory states through multiple collaborating memory experts and employs a novel Time-Aware Linear Attention (TALA) mechanism, which leverages learnable exponential decay functions and positional biases to dynamically update memory. This design enables the model to selectively reinforce important historical information while effectively mitigating memory dilution, substantially improving long-range dependency modeling. Experiments on long-sequence text and image generation tasks demonstrate that MixFormer not only achieves significant performance gains but also provides a more sustainable computational backbone for the next generation of web infrastructure.

Yu Guo, Lei Duan

School of Computer Science, Sichuan University Chengdu, China · School of Artificial Intelligence, Sichuan University Chengdu, China

Memory-Augmented Neural Networks Transformer Long-Context Modeling Linear Attention Mixture-of-Experts Models

Aug 9, 2026cs.CV

VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling

Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-attention. Current solutions either resort to aggressive token pruning, risking irreversible information loss, or adopt efficient but less precise architectures, while largely ignoring the equally vital textual component. We introduce VLZip, a framework that unifies visual and textual compression for high-fidelity reasoning within a pure Transformer. At its core, VLZip hierarchically distills visual and textual segments into compact, layer-specific "soft prefixes" and injects them into each decoder layer's hidden states, drastically shortening the attention sequence while preserving fine-grained global context. To address deficient evaluations in the field, we also introduce LongVLBench, a new benchmark derived from video narratives that demands holistic, narrative-level reasoning. Extensive experiments show VLZip achieves leading performance on long-context multimodal reasoning, enabling training up to 120K tokens, a 6x increase over the baseline, and inference beyond 280K tokens with significantly reduced memory, while demonstrating the memory scalability to handle up to 2M tokens. By excelling at extreme context lengths where existing methods collapse, VLZip establishes an efficient and powerful new standard for long-context multimodal AI. Code is available at https://github.com/ShareLab-SII/VLZip.

Yuqi Zhang, Cheng Chen, Yuyu Guo +6

Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, China · Shanghai Innovation Institute, China · Ant Group, China

Vision-Language Models Efficient VLM Inference Long-Context Modeling Multimodal Token Compression Long-Context VLMs

Aug 9, 2026cs.CL

Position Encoding in Transformers: From Absolute and Relative Methods to Rotary Position Embeddings and Long-Context Scaling

Self-attention models content-dependent interactions between tokens but does not by itself encode token order. Position encoding addresses this limitation by introducing absolute coordinates, relative distances, or position-dependent rotations into Transformer representations and attention scores. This technical survey develops a unified account of sinusoidal and learned absolute position embeddings, Shaw-style relative position representations, Transformer-XL, T5 relative position bias, ALiBi, and Rotary Position Embeddings (RoPE). We derive how RoPE converts absolute position indices into relative phase differences in Query-Key inner products and compare these methods in terms of where position is injected, computational cost, compatibility with KV caching, and length extrapolation. We then examine long-context extensions, including Position Interpolation, RoPE scaling laws, NTK-aware scaling, Dynamic NTK, NTK-by-parts, YaRN, LongRoPE, and LongRoPE2, with emphasis on frequency allocation, attention rescaling, training length, and target context length. We also summarize implementation considerations, evaluation protocols, and position-encoding choices in representative large language models. A central conclusion is that the ability to compute positional features beyond the training length does not imply reliable long-context generalization; context extension must be evaluated through short-context retention, position-wise perplexity, retrieval, reasoning, and long-context code tasks.

Jiguo Li

Rotary Positional Embeddings Long-Context Modeling Positional Encoding LLM Context Management

Aug 4, 2026cs.LG

TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series

Precise anomaly localization over long-context time series is a crucial task in monitoring applications across clinical care, industrial operations, financial services, and logistics, where brief evidence may hide inside long spans of high-frequency data. Time-Series Language Models (TSLMs) are able to ingest time series data and verbalize findings on anomalies in natural language; however, recent benchmarks report a decrease in retrieval performance at long contexts, mirroring failure modes in text, vision, and audio. In the text domain, Recursive Language Models (RLMs) can recover much of this lost performance by keeping context external to the large language model (LLM), allowing the model to query it through code. We present TimeRLM, an RLM formulation for time-series that sequentially manipulates the signal using code and vision capabilities. We further introduce AnomalyXL, a synthetic long-context anomaly localization benchmark with programmatically injected anomalies that require precise retrieval. We implement five different task categories and two variants: AnomalyXL-MCQ and AnomalyXL-Localize. TimeRLM outperforms every evaluated TSLM and single-pass baseline on four of the five AnomalyXL-Localize tasks, reaching 0.682 IoU on localization and 0.745 on classify-with-evidence, versus at most 0.329 and 0.072 across all baselines. We post-train TimeRLM using reinforcement learning. The resulting model further improves performance and requires approximately one-third as many agent interaction turns as its untrained base model to produce a final answer. On unseen real-world ECG, sleep and software observability recordings, the post-trained TimeRLM retains or improves performance, surpassing TSLMs despite being trained exclusively on synthetic data. Our findings suggest recursive interaction with time-series is an effective approach for long-horizon retrieval.

Nicolas Zumarraga, Lorenzo Steno, Ning Wang +9

1Agentic Systems Lab, ETH Zürich · 3Seldon Technologies · 2Stanford University +4

Anomaly Localization Long-Context Modeling Language Modeling Time-Series Anomaly Detection Recursive Language Models

Aug 3, 2026cs.AI

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing

DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer. However, practical deployment remains constrained by the indexer's expensive

O(L^2)

scoring overhead and the hardware-inefficient, discontinuous memory-access patterns induced by its outputs. To address these system-level bottlenecks, we introduce LongCat Sparse Attention (LSA), a hardware-algorithm co-designed framework comprising three complementary and orthogonal strategies: (1) Streaming-Aware Indexing, which selectively converts scattered KV entries into hardware-aligned contiguous layouts to enable coalesced HBM access; (2) Cross-Layer Indexing, which amortizes indexing overhead by reusing the results produced by a single layer across consecutive layers, supported by cross-layer distillation; and (3) Hierarchical Indexing, which adopts a coarse-to-fine scoring scheme to progressively narrow the candidate set for each query, thereby substantially reducing indexing computation. Extensive scaling experiments, ranging from 69B-A3B to 560B-A27B models, demonstrate that LSA consistently achieves performance on par with full attention across both general-purpose and long-context benchmarks. Moreover, LSA supports native training with context lengths of up to one million tokens and underpins the development of LongCat-2.0 (1.6T-A48B). To facilitate further research, we also introduce and open-source LongCat-Flash-Lite-Sparse (69B-A3B), which integrates LSA into LongCat-Flash-Lite and incorporates an updated long-context training corpus.

Wen Zan, Jiaqi Zhang, Jianchao Tan +11

Meituan LongCat Team

Long-Context Modeling LLM Inference Acceleration Efficient Attention Sparse Attention

Aug 2, 2026cs.CV

Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning

Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthen, models may gradually rely less on visual evidence and more on accumulated textual context, leading to visual forgetting. Existing approaches do not directly constrain how visual evidence is used and maintained along the original reasoning trajectory, leaving long-context visual forgetting insufficiently addressed. To address this issue, we propose Remember-R1, a reinforcement learning framework that mitigates long-context visual forgetting by applying process-level supervision directly on the original reasoning trajectory. Specifically, Remember-R1 introduces rewards that encourage broader coverage of matched visual keywords, stronger persistence of visual dependence in later reasoning steps, and greater focus on question-relevant image regions. Experiments across multiple model scales and diverse multimodal benchmarks demonstrate that Remember-R1 consistently improves reasoning performance. Additional analyses further show that it slows the decline of visual attention during generation, supporting its effectiveness in mitigating long-context visual forgetting.

Jianmin Chen, Jiaqi Tang, Wei Wei +9

Hong Kong University of Science and Technology Hong Kong, China · Northwestern Polytechnical University Xi’an, China · Zhejiang University Hangzhou, China

Vision-Language Models Long-Context Modeling VLM Reasoning RL for VLMs

Jul 23, 2026cs.AI

Naju: A Native Discrete State-Space Model with Independent Retention and Writing for Long-Sequence Memory

Long-sequence memory tracking places two opposing demands on a recurrent state: near-lossless retention of stored bindings over long horizons, and active overwriting of stale ones. In our diagnostic suite, the strongest efficient baselines tend to solve only one side well. Continuous-time-parameterized state-space models (SSMs) such as Mamba obtain their discrete recurrence by zero-order-hold discretization of a continuous-time system; we argue that this detour is unnecessary for memory tracking and parameterize the discrete transition directly. Naju (Native Adaptive Junction Unit) factorizes the recurrent update, schematically

x_n = f_n\odot x_{n-1} + i_n\odot(B_n u_n)

, into an explicit discrete pole (a learned forget gate

f_n

), an independent write gain

i_n

, and input-dependent write/read maps. Since the sigmoid pole satisfies

0<f_n<1

, each frozen local coordinate is Schur-stable by construction, and the full time-varying recurrence satisfies a fading-memory/BIBO bound under uniform boundedness assumptions, with no stability regularizer. We formalize the key structural limitation of coupled designs: any non-expansive complementary single-gate recurrence ties the effective retention

r

and write gain

w

through

|r|+w\le 1

, so near-complete retention forces weak writing; decoupling

f_n

from

i_n

removes this constraint. Empirically, Naju is the only evaluated model that remains strong on both retention and overwriting at 4x the training length. Beyond the diagnostic suite, we evaluate Naju on WikiText-103 language modeling, Long Range Arena, and multi-query associative recall. Across these settings, Naju consistently combines strong long-range memory with competitive or superior performance, outperforming the Mamba baselines in the principal comparisons while remaining competitive with the Transformer and preserving linear-time, linear-memory scaling.

Hyuk Lim, Seunghyun Yoon

Korea Institute of Energy Technology (KENTECH)

Persistent Memory for Language Models Long-Context Modeling State Space Models

Jul 21, 2026cs.CL

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an important frontier. However, we identify a critical failure mode in this regime: \emph{repetitive copying}, where models extensively copy text from the input into their reasoning traces rather than productively solving the problem. We show that this behavior is pervasive across frontier long-context LLMs and intensifies with context length. By separating each prompt into task-relevant key evidence and irrelevant distractor context, we further show that the root cause is insufficient grounding: models copy from the prompt indiscriminately, and those that fail to focus on key evidence are far more likely to answer incorrectly. Motivated by this diagnosis, we propose GEAR (Grounding Evidence-Aware Reward), a reward shaping method that augments the accuracy signal with a grounding reward for overlap with key evidence and a distractor penalty for overlap with irrelevant context. To enable GEAR on natural-language data, we develop an automated pipeline that constructs evidence-annotated training data from arbitrary documents. We validate GEAR across multiple model scales and benchmarks, showing consistent improvements of up to +4.6 average points over standard RL with accuracy-based rewards, with larger gains at longer contexts, while also reducing repetitive copying and thinking length. Our findings suggest that, even as long-context evaluation shifts from simple retrieval toward complex reasoning, accurate grounding in relevant evidence remains an indispensable capability with substantial room for improvement.

Lizhe Fang, Weizhou Shen, Tianyi Tang +1

Peking University · Qwen Team of Alibaba Group · Alibaba Group ATH

LLM Grounding Reward Shaping RL for Language Model Reasoning Long-Context Modeling Data Repetition in Language Model Training

Jul 21, 2026cs.CL

DocAtlas: Long-Document Understanding as Mutable-State Interaction

Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts. Existing retrieval-augmented systems usually select evidence from a static index before generation, while recent agentic systems add multi-turn tool use but often rely on frozen proprietary backbones whose behavior is set by prompts. We present DocAtlas, a system that treats long-document understanding as a mutable-state information-seeking process. We instantiate DocAtlas as a mutable document harness: an external environment that determines what document information is searched, read, stored, reviewed, and shown to the model at each step. Given a document and question, the harness exposes search, reading, note-taking, and review tools, maintains a hierarchical tree and note store, and updates both as the agent records evidence. DocAtlas combines self-improving retrieval, selective evidence access, and active working memory under a fixed context budget. The same harness supports inference-time use with large VLMs and end-to-end reinforcement learning for compact VLM agents. With GPT-5.4, DocAtlas reaches 71.4% on MMLongBench-Doc, exceeding the human-expert reference of 65.8%. A Qwen3.5-4B VLM trained with end-to-end RL in the DocAtlas environment reaches 63.7%, compared with a 54.4% direct-input baseline, showing that mutable document-harness design can improve compact document agents by a large margin.

Hongchen Wei, Yuanzhe Wang, Bei Liu +8

Wuhan University · Microsoft

Document Understanding Long-Context QA Long-Context Modeling Agentic RAG Document QA

Jul 16, 2026cs.LG

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment. The gap is especially important for AI agents, whose observations, tool outputs, documents, and prior decisions accumulate over long trajectories. LongStraw is an architecture-aware execution stack for million-token RL post-training under a fixed GPU budget, instantiated with Group Relative Policy Optimization (GRPO). It evaluates the shared prompt without autograd, retains only model-specific state needed by later tokens, and replays short response branches one at a time, reducing the live training graph at the cost of additional replay time. We implement it for the hybrid recurrent and full-attention Qwen3.6-27B and the compressed-attention mixture-of-experts GLM-5.2. On eight H20 GPUs, LongStraw completes grouped Qwen scoring and response backward at 2.1M positions for groups of 2 and 8; increasing the group size adds only 0.21 GB of peak allocated memory, while a separate stress test reaches 4.46M positions. On 32 H20 GPUs, we validate the end-to-end LongStraw execution path for a 2.1M-token prompt across all 78 layers of GLM-5.2. These experiments establish execution capacity rather than complete training correctness because the captured prompt state is detached and some distributed forward and gradient composition paths remain incomplete.

Changhai Zhou, Kieran Liu, Yuhua Zhou +17

MindLab · Fudan University

Efficient Language Model Training Long-Context Modeling RL Post-Training

Jul 13, 2026cs.CL

Extending LLM Context via Associative Recurrent Memory

Extending the context length of large language models (LLMs) is critical for many real-world applications, yet standard transformers remain constrained by quadratic compute and linear memory scaling. In this work, we investigate the Associative Recurrent Memory Transformer (ARMT) as a practical approach for enabling long-context processing in LLMs, constant memory scaling, and better efficiency. We make three main contributions. First, we construct two domain-specific long-context datasets designed to evaluate realistic workloads, focusing on narrow-domain fine-tuning scenarios. Second, we propose a comprehensive training recipe for ARMT-based context extension, combining continued pre-training, synthetic long-context data generation, curriculum learning, and selective integration of associative memory into chosen model layers. Third, we present an extensive experimental study demonstrating that ARMT-augmented models: (i) process inputs well beyond their original context limits without degrading performance relative to in-limit baselines; (ii) generalize more effectively to out-of-distribution context lengths; and (iii) need 30% less FLOPs while preserving baseline performance within the original context window.

Gleb Kuzmin, Ivan Rodkin, Aydar Bulatov +8

1FusionBrain Lab 2MBZUAI 3Cognitive AI Systems Lab 4RUDN · 2MBZUAI · 6MIRAI +5

Memory-Augmented Language Models Long-Context Language Modeling Recurrent Transformers Long-Context Modeling