Context Compression

Modern large language model (LLM) agents do not simply need longer contexts; they need decision-relevant evidence at the moment of action. We study decision-aware context selection: ranking retrieved files, tests, traces, rules, and memories by their expected effect on an agent's next action rather than by semantic similarity alone. We present the Counterfactual-Inspired Context Layer (CICL), which builds an instance context graph, estimates decision-oriented utility for candidate units, and compresses selected evidence into typed memory cards. The same schema can be instantiated with hosted LLM judges, local surrogates, or lightweight rankers, making the selection protocol auditable across model choices. On 50 SWE-bench Verified file-retrieval instances, Qwen3.6-Plus reranking of BM25 top-50 candidates improves hit@1 from 0.58 to 0.78 and MRR@10 from 0.634 to 0.790, with all 2,500 judgments parseable. Controlled diagnostics show that CICL identifies action-critical evidence: removing the top-utility semantic unit reduces F1 from 0.245 to 0.000. In selected-then-compressed mode, memory cards save 44.93 tokens per query while preserving selected evidence. CICL provides a practical layer for measuring, ranking, and compressing decision-critical context for tool-using agents. Code is available at https://github.com/stephen-guan-researcher/CICL.

Web agents operating over long horizons ingest raw DOM and accessibility trees -- routinely tens of thousands of tokens -- at every action step, causing progressive context degradation that erodes reasoning well before tasks complete. We argue that this coupling of observation frequency to action frequency is an architectural mistake. Drawing on the insight from Recursive Language Models that querying a document outperforms reading it wholesale, we propose Signal-Driven Observation (SDO): a dedicated sub-call reads the full DOM but returns only task-relevant elements and their selectors, and is re-invoked only when a lightweight signal detector fires -- triggered by URL transitions, newly visible interactive elements, action failures, or exogenous browser events. We outline the open problems SDO introduces and call on the community to treat observation compression as a core architectural decision in web agent design.

Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward model that estimates the forecasting utility of each article and uses this signal to allocate compression budgets during sequential pairwise fusion, preserving informative content within a fixed context limit. Second, we introduce a process reward model (PRM) that ranks multiple supplementary-news candidates conditioned on the current error profile and the history of previously selected articles, replacing one-shot blind retrieval with quality-controlled selection. Both components are trained offline using historical data with ground truth; inference uses the frozen filtering logic and compression modules without any reflection loop. Experiments on finance, energy, traffic, and bitcoin forecasting benchmarks show that our method improves prediction accuracy over strong baselines, significantly reduces the number of refinement iterations compared to the iterative baseline, and remains effective when relevant articles span thousands of tokens.

If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how faithfully a system captures a person's interpretation. An interpretive layer is operationalized as a Behavioral Specification. Our reference implementation aggressively compresses a person's data into interpretive patterns, served as context to a language model. We evaluate the Specification on a prototype benchmark of held-out behavioral predictions scored by a calibrated 5-judge LLM panel. We test it independently and in composition with a range of context conditions: full raw corpus, full extracted facts, and four commercial memory systems (Mem0, Letta, Supermemory, Zep). Across 14 public-domain autobiographical corpora, the Specification lifts representational accuracy in aggregate and nearly eliminates model hedging. It recovers most of what the raw corpus delivers, at ~25x less context cost. The Specification lifts subjects toward a common predictive level regardless of pretraining baseline; the lift in absolute points is therefore largest where the baseline is lowest, suggesting the population of relevance is anyone not adequately represented in pretraining. Lift is greatest on interpretation-required questions, where providing an interpretive layer enables model behavior that extracted facts or raw corpus do not. Conversely, on recall-required questions, this layer can interfere rather than help. We conclude that representational accuracy is distinct from recall and that human-AI alignment is dependent on how accurately the user is represented. Representational accuracy makes that alignment testable.

Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown promise, they typically rely on complex compression modules or compression-specific training, leaving the intrinsic capabilities of LLMs underexplored. In contrast, this work reveals that a thinking model itself can naturally compress long contexts by organizing task-relevant information. We thus derive Thinking as Compression (TaC), a new compression paradigm that treats thinking itself as compressed context. Without relying on specific dedicated compressor, TaC directly prompts the thinking model to generate thinking traces as the shortened context, already outperforming most representative compression methods. Further, given that raw thinking output may struggle with budget control and shortcut behaviors, we introduce Thinking as Compression Constrained (TaC-C), leveraging a simple reward-driven optimization framework to elicit intrinsic thinking as compact and controllable compressed context. Experiments across four long-context QA benchmarks demonstrate that TaC-C consistently outperforms existing baselines. At 4x and 8x compression ratios, it surpasses the strongest competitor by 17.4% and 23.4% in average F1, and by 15.7% and 21.7% in average Exact Match Score (EM), respectively.

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and embedding filters. Framed as offline multi-label retrieval over three public datasets spanning social-media, legal, and smart-home sensor domains (six LLMs, seven baselines), our central contribution is a two-crossover cost-accuracy characterisation: an analytical context-window crossover below which a CoverAndMerge compression pipeline reduces LLM invocations, and an empirical discrimination-capacity crossover above which matching accuracy collapses independently of context budget, by a model-dependent factor of parameter count and training generation. Two findings carry practical weight: above the discrimination crossover, compression cannot recover accuracy and only frontier-scale models clear large subscription sets; and there backend choice dominates configuration choice, so model selection, not pipeline tuning, is the primary operator lever. We accompany this with three composable algorithms and a per-cluster Quality-of-Experience framework for autonomic LLM-tier selection.

Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that an LLM can expand into task-relevant meaning. We call this setting SemanticZip. Unlike lossless compression, SemanticZip does not require byte-identical reconstruction; unlike ordinary summarization, it treats model-based decompression as part of the codec and evaluates whether task-relevant semantic commitments are recovered. This paper is a pilot framework, not a benchmark claim. We formalize LLM-mediated decompression, define a protected/lossy packet architecture, and evaluate six representation regimes over five author-constructed diagnostic cases: structured prose, JSON, CCL-Core, CCL-Min, SemanticZip ASCII, and SemanticZip emoji. An independent decoder LLM reconstructs typed semantic atoms from each compressed representation, and we score Critical Atom Recall, Weighted Atom Recall, precision, and tokenizer gain. In this pilot, structured prose has the highest recoverability, with WAR = 0.956 and 19.1% o200k_base token gain. CCL-Min is the strongest balanced point, with 39.4% token gain and WAR = 0.874. SemanticZip ASCII provides the largest useful compression, with 46.5% token gain and WAR = 0.802, while emoji-heavy SemanticZip performs worse on both compression and recovery. The main contribution is not the claim that these numbers establish a universal frontier. Rather, we introduce a reproducible experimental interface for studying lossy, LLM-decompressible text codes and a design principle: safety-critical and exact commitments should remain protected, while predictable low-risk context may be semantically zipped.

LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens, enabling denser information storage. We apply the recently proposed In-Context Autoencoder for this purpose. While the method performs well on single-shot common-knowledge and code-understanding tasks, our experiments demonstrate that it fails on multi-step agentic coding tasks. In this paper, we explore this phenomenon and discuss possible factors contributing to this failure.

Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces high computational overhead and information redundancy. While soft prompt compression has emerged as a promising way to mitigate these costs by compressing sequences into compact embeddings, existing paradigms remain fundamentally constrained by position bias: they primarily rely on learnable tokens insertion at fixed positions or group tokens according to their physical token layout, thereby inducing performance instability and semantic fragmentation. To overcome this bottleneck, we propose Semantic Consistency Context Compression (SeCo), a method that shifts context compression from position-driven to semantic-driven. Rather than constraint by physical token layout, SeCo dynamically anchors compression directly in the semantic space by selecting query-relevant tokens as semantic centers and aggregating remaining tokens via consistency-weighted merging. This design inherently preserves semantic consistency while eliminating position bias. Extensive experiments on 14 benchmarks across two backbone models demonstrate that SeCo consistently shows superiority in downstream tasks, inference latency, and out-of-domain robustness. The code is available at https://anonymous.4open.science/r/seco-EE5E.

Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort. Context compression is also a challenging and pressing task, which is vital to reasoning-driven generation, and agentic tasks requiring long context and continual learning. In this paper, we explore how to unify reasoning-driven generation, reasoning-enhanced text representation and context compression tasks in one forward pass for LLMs. Through meta latent tokens and a unified generative, representative and compressive tuning approach, we propose a training framework named GRC that bridges the three tasks. The trained models can accomplish three objectives in a single forward pass while maintaining modular, LEGO-style flexibility during inference. This design greatly reduces the deployment effort for retrieval-augmented generation (RAG) and achieves efficient inference and three times data utilization during training. Furthermore, this framework design enables a new paradigm for text embedding: self-reason-latent embeds, and a new generation paradigm, latent memory-augmented generation, where compressed and internalized KV cache with O(1) length is used as the updatable memory. We also propose hybrid paged attention to speed up the inference of our models. Extensive experiments on reasoning-intensive retrieval benchmarks, generative tasks, document compression, latency evaluation, and RAG settings demonstrate the effectiveness of our method and may shed light on the truly unified model that can handle reasoning-driven generation, embedding and compression tasks seamlessly.

A growing body of work in cognitive science suggests that reportable conscious access is associated with global ignition over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of Mindscape Activation Signature (MiA-Signature), a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks.

AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding. The accessibility tree is a commonly used text-based format that encodes UI element attributes, but it suffers from redundancy and lacks structural information such as spatial relationships among elements. We propose A11y-Compressor, a framework that transforms linearized accessibility trees into compact and structured representations. Our implementation, Compressed-a11y, applies a lightweight and structured transformation pipeline with modal detection, redundancy reduction, and semantic structuring. Experiments on the OSWorld benchmark show that Compressed-a11y reduces input tokens to 22% of the original while improving task success rates by 5.1 percentage points on average.

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the standard softmax attention exhibits quadratic time complexity with respect to sequence length. As the sequence length increases, this incurs substantial overhead in long-context settings, leading the training and inference costs of extremely long sequences deteriorate rapidly. Existing solutions mitigate this issue through two technique routings: i) Reducing the KV cache per layer, such as from the head-level compression GQA, and the embedding dimension-level compression MLA, but the KV cache remains linearly dependent on the sequence length at a 1:1 ratio. ii) Interleaving with KV Cache friendly architecture, such as local attention SWA, linear kernel GDN, but often involve trade-offs among KV Cache and long-context modeling effectiveness. Besides the two technique routings, we argue that there exists an intermediate path not well explored: {Maintaining a linear relationship between the KV cache and sequence length, but performing semantic-level compression through a specific ratio $k$}. This $O(n/k)$ path does not pursue a ``minimum KV cache'', but rather trades acceptable memory costs for complete, referential, and interpretable retention of long distant dependency. Motivated by this, we propose Kwai Summary Attention (KSA), a novel attention mechanism that reduces sequence modeling cost by compressing historical contexts into learnable summary tokens.

Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM introduces two critical bottlenecks: the "lost in the middle" phenomenon degrades ranking quality as input length grows, and the inference latency scales super-linearly with sequence length, rendering it impractical for industrial deployment. In this paper, we present ResRank, a unified retrieval-reranking framework that fundamentally addresses both challenges. Inspired by multimodal LLMs that project visual inputs into compact token representations, ResRank employs an Encoder-LLM to compress each candidate passage into a single embedding, which is then fed alongside the query text into a Reranker-LLM for listwise ranking. To alleviate the misalignment between the compressed representation space and the ranking space, we introduce a residual connection structure that combines encoder embeddings with contextualized hidden states from the reranker. Furthermore, we replace the conventional autoregressive decoding with a one-step cosine-similarity-based scoring mechanism, eliminating the generation bottleneck entirely. ResRank is trained through a carefully designed dual-stage, multi-task, end-to-end joint optimization strategy that simultaneously trains the encoder and reranker, achieving learning objective alignment between retrieval and reranking while substantially reducing training complexity. Extensive experiments on TREC Deep Learning and eight BEIR benchmark datasets demonstrate that ResRank achieves competitive or superior ranking effectiveness compared to existing approaches while requiring zero generated tokens and processing only one token per passage, yielding a fundamentally better balance between effectiveness and efficiency.

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves useful environment feedback, but also leads to context saturation and high token cost; conversely, naive compression may discard task-critical signals needed for subsequent actions. Because terminal environments are highly heterogeneous across repositories, commands, and execution states, heuristic-based or fixed-prompt compression methods are difficult to generalize. We propose TACO, a plug-and-play, training-free, self-evolving Terminal Agent Compression framework for existing terminal agents. TACO automatically discovers, refines, and reuses structured compression rules from interaction trajectories, enabling workflow-adaptive filtering of low-value terminal outputs while preserving task-relevant observations. Experiments on TerminalBench (TB 1.0 and TB 2.0) and four additional terminal-related benchmarks, including SWE-Bench Lite, CompileBench, DevEval, and CRUST-Bench, show that TACO consistently improves task performance and token efficiency across agent scaffolds and backbone models. On TerminalBench, TACO yields 1%-4% accuracy gains across strong agentic models and improves accuracy by around 2%-3% under the same token budget. On additional terminal-related benchmarks, it reduces total token consumption while maintaining or improving task success rates. These results suggest that self-evolving, workflow-adaptive observation compression is an effective path toward more reliable and efficient long-horizon terminal agents. The code is publicly available at https://github.com/multimodal-art-projection/TACO.

Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. However, the effectiveness of RAG depends not only on the design of the retriever and the capacity of the underlying model, but also on how retrieved evidence is structured and aligned with the query. Existing RAG approaches typically retrieve and concatenate unstructured text fragments as context, which often introduces redundant or weakly relevant information. This practice leads to excessive context accumulation, reduced semantic alignment, and fragmented reasoning chains, thereby degrading generation quality while increasing token consumption. To address these challenges, we propose Tri-RAG, a structured triplet-based retrieval framework that improves retrieval efficiency through reasoning-aligned context construction. Tri-RAG automatically transforms external knowledge from natural language into standardized structured triplets consisting of Condition, Proof, and Conclusion, explicitly capturing logical relations among knowledge fragments using lightweight prompt-based adaptation with frozen model parameters. Building on this representation, the triplet head Condition is treated as an explicit semantic anchor for retrieval and matching, enabling precise identification of query-relevant knowledge units without directly concatenating lengthy raw texts. As a result, Tri-RAG achieves a favorable balance between retrieval accuracy and context token efficiency. Experimental results across multiple benchmark datasets demonstrate that Tri-RAG significantly improves retrieval quality and reasoning efficiency, while producing more stable generation behavior and more efficient resource utilization in complex reasoning scenarios.

Large Language Models (LLMs) struggle with long-horizon tasks due to the "context bottleneck" and the "lost-in-the-middle" phenomenon, where accumulated noise from verbose environments degrades reasoning over multi-turn interactions. To address this issue, we introduce a symbiotic framework that decouples context management from task execution. Our architecture pairs a lightweight, specialized policy model, ContextCurator, with a powerful frozen foundation model, TaskExecutor. Trained via reinforcement learning, ContextCurator actively reduces information entropy in the working memory. It aggressively prunes environmental noise while preserving reasoning anchors, that is, sparse data points that are critical for future deductions. On WebArena, our framework improves the success rate of Gemini-3.0-flash from 36.4% to 41.2% while reducing token consumption by 8.8% (from 47.4K to 43.3K). On DeepSearch, it achieves a 57.1% success rate, compared with 53.9%, while reducing token consumption by a factor of 8. Remarkably, a 7B ContextCurator matches the context management performance of GPT-4o, providing a scalable and computationally efficient paradigm for autonomous long-horizon agents.

Machine data is central to observability and diagnosis in modern computing systems, appearing in logs, metrics, telemetry traces, and configuration snapshots. When provided to large language models (LLMs), this data typically arrives as a mixture of natural language and structured payloads such as JSON or Python/AST literals. Yet LLMs remain brittle on such inputs, particularly when they are long, deeply nested, and dominated by repetitive structure. We present HYVE (HYbrid ViEw), a framework for LLM context engineering for inputs containing large machine-data payloads, inspired by database management principles. HYVE surrounds model invocation with coordinated preprocessing and postprocessing, centered on a request-scoped datastore augmented with schema information. During preprocessing, HYVE detects repetitive structure in raw inputs, materializes it in the datastore, transforms it into hybrid columnar and row-oriented views, and selectively exposes only the most relevant representation to the LLM. During postprocessing, HYVE either returns the model output directly, queries the datastore to recover omitted information, or performs a bounded additional LLM call for SQL-augmented semantic synthesis. We evaluate HYVE on diverse real-world workloads spanning knowledge QA, chart generation, anomaly detection, and multi-step network troubleshooting. Across these benchmarks, HYVE reduces token usage by 50-90% while maintaining or improving output quality. On structured generation tasks, it improves chart-generation accuracy by up to 132% and reduces latency by up to 83%. Overall, HYVE offers a practical approximation to an effectively unbounded context window for prompts dominated by large machine-data payloads.

LLM-based agents show strong potential for long-horizon reasoning, yet their context size is limited by deployment factors (e.g., memory, latency, and cost), yielding a constrained context budget. As interaction histories grow, this induces a trade-off between retaining past information and staying within the context limit. To address this challenge, we propose Budget-Aware Context Management (BACM), which formulates context management as a sequential decision problem with a context budget constraint. It enables agents to assess the available budget before incorporating new observations and decide when and how much of the interaction history to compress. We further develop BACM-RL, an end-to-end curriculum-based reinforcement learning approach that learns compression strategies under varying context budgets. Experiments on compositional multi-objective QA and long-horizon web browsing benchmarks show that BACM-RL consistently outperforms prior methods across model scales and task complexities, achieving over $1.6\times$ gains over strong baselines in high-complexity settings, while maintaining strong advantages as budgets shrink, where most methods exhibit a downward performance trend.

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression framework that integrates importance-aware memory selection, coherence-sensitive filtering, and dynamic budget allocation to retain essential conversational information while controlling context growth. The approach is evaluated on LOCOMO, LOCCO, and LongBench benchmarks to assess answer quality, retrieval accuracy, coherence preservation, and efficiency. Experimental results demonstrate that the proposed method achieves consistent improvements in conversational stability and retrieval performance while reducing token usage and inference latency compared with existing memory and compression-based approaches. These findings indicate that adaptive context compression provides an effective balance between long-term memory preservation and computational efficiency in persistent LLM interactions

Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to account for the extreme variance in natural language information density. While adopting a density-aware dynamic compression ratio seems intuitive, empirical investigations reveal that models struggle intrinsically with operations parameterized by input dependent, continuous structural hyperparameters. To resolve this pitfall, we introduce Semi-Dynamic Context Compression framework. Our approach features a Discrete Ratio Selector, which predicts a compression target based on intrinsic information density and quantizes it to a predefined set of discrete compression ratios. It is efficiently jointly trained with the compressor on synthetic data, with the summary lengths as a proxy to create labels for compression ratio prediction. Extensive evaluations confirm that our density-aware framework, utilizing mean pooling as the backbone, consistently outperforms static baselines, establishing a robust Pareto frontier for context compression techniques. Our code, data and model weights are available at https://github.com/yuyijiong/semi-dynamic-context-compress

While context compression can mitigate the growing inference costs of Large Language Models (LLMs) by shortening contexts, existing methods that specify a target compression ratio or length suffer from unpredictable performance degradation, hindering their reliable deployment. We introduce a paradigm shift to Performance-oriented Context Compression (PoC), where developers specify an acceptable performance floor instead of a compression ratio. PoC employs a lightweight performance predictor to automatically find the most aggressive compression ratio that satisfies this constraint before steering an off-the-shelf compressor. We design and compare two predictor variants: a simple context-agnostic predictor and a more sophisticated context-aware one that considers the input's inherent compressibility. On both question-answering and summarization benchmarks, the context-aware predictor consistently achieves lower performance prediction error than the context-agnostic predictor, while the resulting context-aware PoC attains a superior overall performance. Our work paves the way for a more reliable, efficient, and performance-aware deployment of context compression for LLMs.

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

Efficient context compression is critical for retrieval-augmented question answering in resource-constrained settings, where long retrieved contexts increase latency, memory use, and LLM reader cost. We propose a lightweight encoder-only framework for query-driven sentence pruning that preserves answer-critical evidence while aggressively reducing irrelevant context. Our method learns marginal contribution scores for sentences using counterfactual training signals and optimizes a contrastive ranking objective that separates critical evidence from noncritical context. Our approach scores all sentences from a single full-context encoding, enabling fast inference with low computational overhead. Experiments show that it maintains accuracy comparable to the strongest baseline while using 3.7$\times$ less peak memory and achieving nearly 3$\times$ lower compression latency, demonstrating an effective quality--efficiency trade-off for practical resource-constrained deployment.

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs. To address this challenge, we propose~\modelname, a novel framework based on multi-grained context compression and query-aware information acquisition. SharedLLM comprises two stacked short-context LLMs: a lower model serving as a compressor and an upper model acting as a decoder. The lower model compresses long inputs into compact, multi-grained representations, which are then forwarded to the upper model for context-aware processing. To maximize efficiency, this information transfer occurs exclusively at the lowest layers, bypassing lengthy forward passes and redundant cross-attention operations. This entire process, wherein the upper and lower models are derived from the same underlying LLM layers, is termed~self-injection. To support this architecture, a specialized tree-based data structure enables the efficient encoding and query-aware retrieval of contextual information. Despite being trained on sequences of only 8K tokens, \modelnameeffectively generalizes to inputs exceeding 128K tokens. Across a comprehensive suite of long-context modeling and understanding benchmarks, \modelnameachieves performance superior or comparable to strong baselines, striking an optimal balance between efficiency and accuracy. Furthermore, these design choices allow \modelname~to substantially reduce the memory footprint and yield notable inference speedups ($2\times$ over streaming and $3\times$ over encoder-decoder architectures).

In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant responses. We revisit this design choice by comparing full-context prompting to four alternative, substantially-reduced context configurations. Analyzing in-the-wild multi-turn conversations across three open reasoning and one state-of-the-art model, we find that response quality is largely preserved under aggressive context filtering: replacing all prior assistant turns with one-sentence summaries or keeping only the most recent user--assistant exchange often matches storing full context in performance while using roughly 8x less context. To understand this result, we observe that a substantial fraction of user turns (36.4%) in multi-turn conversations are self-contained and that many follow-up turns can be addressed by seeing only the immediately preceding user--assistant exchange. Furthermore, we find that when models condition on their own past responses, this can lead to context pollution, a phenomenon in which reasoning errors, hallucinations, or stylistic artifacts propagate across turns. Motivated by these findings, we design a context-filtering approach that selectively omits the assistant-side history. Taken together, these findings suggest moving away from storing full dialogue transcripts and instead retaining only what is relevant.

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

Processing long documents with large language models (LLMs) is expensive: a single query over a 100K-token document can cost from tens of cents to over a dollar in API fees, depending on the model, and memory grows linearly with context length. We introduce BudgetMem, a training-free architecture that keeps only high-salience content under an explicit memory budget. Unlike token-level neural compressors such as LLMLingua, BudgetMem makes chunk-level keep-or-discard decisions from interpretable features: entity density, TF-IDF importance, position, numerical density, discourse markers, and question presence. Across four benchmarks, BudgetMem matches the uncompressed baseline on template-generated structured documents (F1 = 0.859 vs. 0.855) while discarding 70% of chunks. As a pre-retrieval filter on the same documents it outperforms LLMLingua-2 by a wide margin (0.859 vs. 0.554), because token-level compression destroys the phrasal structure that retrieval depends on; the advantage holds across model scale and family (Llama-3.2-3B, Qwen2.5-7B), under dense retrieval (0.918 vs. 0.530), and in LLMLingua-2's intended direct-feed mode (0.797 vs. 0.720). On real NLP research papers (Qasper), BudgetMem is competitive but not free, trailing the full baseline by 7.4% and LLMLingua-2 by 5.5% relative F1 at a 72% storage reduction. Removing discourse markers or numerical density hurts most, although TF-IDF alone scores as well on template documents. The pipeline needs no trained models or GPU for compression and runs on a $10/month Colab instance.

Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent representations, have shown promise, their real-world adoption is limited. Existing techniques typically compress the context as a single unit, which leads to quadratic compression complexity and an inability to reuse computations across queries with overlapping contexts. In this work, we introduce CompLLM, a soft compression technique designed for practical deployment. Instead of processing the context holistically, CompLLM divides it into segments and compresses each one independently. This simple design choice yields three critical properties: efficiency, as the compression step scales linearly with the context length; scalability, enabling models trained on short sequences (e.g., 1k tokens) to generalize to contexts of 100k tokens; and reusability, allowing compressed segments to be cached and reused across different queries. Our experiments show that with a 2x compression rate, at high context lengths CompLLM speeds up Time To First Token (TTFT) by up to 4x and reduces the KV cache size by 50%. Furthermore, CompLLM achieves performance comparable to that obtained with the uncompressed context, and even surpasses it on very long sequences, demonstrating its effectiveness and practical utility.

Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than mere knowledge regurgitation. Leveraging the strong contextual reasoning abilities of large language models (LLMs), in-context learning (ICL) becomes a promising editing method by comprehending edit information through context encoding. However, this method is constrained by the limited context window of LLMs, leading to degraded performance and efficiency as the number of edits increases. To overcome this limitation, we propose InComeS, a flexible framework that enhances LLMs' ability to process editing contexts through explicit compression and selection mechanisms. Specifically, InComeS compresses each editing context into the key-value (KV) cache of a special gist token, enabling efficient handling of multiple edits without being restricted by the model's context window. Furthermore, specialized cross-attention modules are added to dynamically select the most relevant information from the gist pools, enabling adaptive and effective utilization of edit information. We conduct experiments on diverse model editing benchmarks with various editing formats, and the results demonstrate the effectiveness and efficiency of our method.