Local Windows

Retrieval-augmented generation (RAG) can improve knowledge-intensive question answering, but the first design choice is easy to overlook: how should the source corpus be partitioned into retrievable units? Fixed-size chunks often return long passages whose relation to the question is only implicit. We introduce EAR, an Entity-Aware Partitioning approach for multiple-choice question answering (MCQA). EAR extracts normalized surface anchors from the question, answer options, and corpus; retrieves local windows around matching corpus anchors; and can attach a larger parent passage through an extractive summary. We evaluate EAR on a cleaned Massive Multitask Language Understanding (MMLU)-style subset of 153 questions selected by an automatic corpus-support heuristic and using decontaminated public textbook text. Across same-protocol top-k = 3 and top-k = 8 sweeps with Mistral, Gemma, and DeepSeek, EAR entity-window reduces retrieved words by 37.5-40.2% relative to chunks. Observed accuracy changes are +5.2, +1.3, and -3.9 points at top-k = 3, and +5.9, -3.3, and -4.6 points at top-k = 8; none of the entity-window differences is statistically significant. The scoped contribution is methodological: EAR provides a compact and inspectable retrieval unit, while its rule-based anchor extractor remains domain-specific and requires separate validation before transfer.

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.

Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically overcorrect and degrade $F_{0.5}$ by rewriting well-formed spans. While fine-tuning provides an effective solution, it imposes substantial infrastructure demands. We introduce a prompt-based approach that closes the gap to fine-tuned models through three advances in GEC prompting methodology. First, we introduce taxonomy-based instructions to enforce minimal-edit constraints with a comprehensive list of grammatical error rules, equipping the LLM with a bounded, metric-aligned scope of correctable edits, which benefits the strongest models while remaining model-dependent overall. Second, we show that batching multiple uncorrected sentences into a single input context acts as a targeted regularizer against overcorrection, systematically reducing the edit rate across diverse LLM families; we hypothesize this arises from attention dilution effect induced by the bounded capacity of self-attention scores. Finally, LLM-assisted Prompt Optimization refines these instructions. Powered by Gemini 3.1-Pro, our prompt achieves $F_{0.5}=78.32$ on the BEA-2019 test set - establishing a new prompt-based SOTA while shrinking the gap to the fine-tuned single-model SOTA (Staruch et al., 2025) to a mere $0.38$ points. Code, prompts, and outputs are publicly available.

The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks. However, the trial-and-error nature of these agents generates lengthy interaction trajectories, creating severe bottlenecks in terms of context window limits and cost. While context compression offers a potential remedy, prior approaches suffer from static pruning strategies and granularity mismatches, often failing to preserve the semantic dependencies and syntactic details crucial for SE tasks. To strictly preserve critical task evidence while reducing context length, we introduce AttnCompress, a dynamic attention-guided trajectory compression framework. Unlike existing approaches, AttnCompress bridges the gap between semantic integrity and dynamic adaptability through three key mechanisms: (1) structure-aware segmentation via perplexity (PPL) spikes to preserve the syntactic structure of code and logs; (2) relevance estimation using proxy attention weights to quantify the precise relevance of historical blocks to the agent's current reasoning; and (3) a dynamic rolling window to re-evaluate and recall historical context as the task evolves. Extensive evaluation on SWE-Bench-Verified and Multi-SWE-Bench demonstrates that AttnCompress achieves a pass rate of 53.17%, outperforming prior state-of-the-art baselines while reducing token consumption by 21.6% and total costs by 33.6%. The framework proves to be model-agnostic and generalizes effectively across diverse programming languages.

Recent Relational Deep Learning architectures have been proposed as foundation models for multi-table relational data, yet they impose constrained neighborhood budgets that force row truncation when an entity has many related records. We introduce Animus, a synthetic financial dataset in which predicting customer income requires aggregating up to tens of thousands of transactions. On the raw representation, three recently proposed models (RT, Griffin, RelGT) achieve $R^2 \le 0.18$; a single, routine, temporal pre-aggregation step recovers $R^2$ up to $0.65$. This questions whether current relational foundation models are ready for high-cardinality real-world data.

Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window. Existing compaction methods address this limitation by discarding, summarizing, or retrieving earlier information, but they may remove task-critical details or fail to recover them reliably. We propose ARC (Addressable Recall Compaction), a context-management framework that separates archival storage from active-context presentation. ARC stores tool observations in an append-only, ID-addressable log and replaces older observations with compact citations when compaction is required. The agent can subsequently use these identifiers to request stored content without re-executing the corresponding tools or depending solely on similarity-based retrieval. We evaluate ARC using Qwen3-8B with a 16k context window and Qwen3-32B with a 32k context window. On the Needle-in-a-Haystack evaluation, ARC achieves an average exact-answer accuracy of 99.40%, compared with 88.12% for the best-performing baseline in our evaluation. ARC also reduces estimated serving time and HBM traffic under our hardware-cost model. On the LongBench-v2 Hard subset, ARC obtains an average accuracy of 29.97%, compared with 28.25% for the best-performing baseline. These results indicate that explicit, address-based recall can improve information retention and serving efficiency relative to the evaluated context-management baselines under the tested settings.

Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations. The incumbent response treats this as a storage-and-retrieval problem. We argue that framing is too narrow. Actively managing what an agent holds in mind is a lifecycle, not merely a store: it spans deciding what to remember, extracting and structuring it, choosing the right store per data type, consolidating and forgetting while preserving provenance, deciding what is relevant now, anticipating what is needed next, and compacting context to a budget without losing what matters. In serious production this operates not over a single user but across an organizational scope hierarchy. We name this discipline Agentic Context Management (ACM) and decompose it into five primitives: architecting, ingesting, scoping, anticipating, and compacting & consolidation. We then make the economic case: naive context accumulation grows token cost quadratically in conversation length, crude summarization buys linear cost at the price of an accuracy cliff, and only validated compaction achieves linear cost with preserved fidelity. We describe a reference implementation, Maximem Synap, that realizes the five primitives as a multi-tenant service and reports 92% on LongMemEval and 93.2% on LoCoMo under the configuration detailed in Section 6. We close with dimensions existing benchmarks do not yet capture, latency, token efficiency, and context-rot resistance, and the frontier of decision-level and organization-level context the category points toward.

Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning. However, recent studies have shown that they struggle to reliably solve planning problems. At the same time, theoretical results have shown that transformers, the core architecture underlying modern LLMs, are Turing-complete. In this work, we investigate this apparent gap between the theoretical computational power of LLMs and their empirical planning performance. We propose Chain of Computation (COC), a computational architecture that places a transformer-based LM inside an iterative loop, leveraging its strength as a pattern-matching system. The COC uses a Structured Context Window (SCW) which provides a constant-sized context window with support for choosing which window is used at each planning step. Within this architecture, the LM is able to learn a planning policy, predicts the world model, and performs the arithmetic operations required during planning. We show that, when given an append-only SCW (resembling a Turing Machine tape), even relatively small LMs trained from scratch can learn planning policies and generalize from a small number of training instances within each planning domain, achieving success rates above 99.89% on BlocksWorld and the Pancake puzzle. Our analysis of failure cases in Tower of Hanoi (TOH) reveals that they arise from arithmetic operations or from encountering previously unseen tokens. We show that COC can solve TOH problem instances with up to 20 disks, requiring over 1 million actions, while requiring substantially less training data by either (1) planning with symbolical support for arithmetic or by (2) using a deterministic pushdown automaton (PDA) formulation for the SCW.

Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task. This creates a practical allocation problem: every token spent on coordination is unavailable to task instructions or evidence when a call is assembled under a fixed context budget. We introduce the Roundtable Context Window Test (RCWT), a controlled protocol for measuring this task-budget displacement effect. RCWT varies coordination content while controlling total budget, position order, task family, and scoring. In the main context-dependent recall task at $W=4096$, three commercial models remain near baseline through moderate overhead and then degrade sharply once residual reference evidence falls to a few hundred tokens. Window-scaling summaries are consistent with a task-specific residual-budget interpretation rather than a fixed percentage threshold, but we treat this as descriptive evidence rather than a universal law. To test whether the fixed-budget cliff persists when task evidence remains intact, we add an intact-task ablation: the full task/reference block is kept present while coordination tokens increase by expanding total prompt length. In that setting, all tested calls return every scored field correctly across GPT-4.1-mini, Claude Haiku 4.5, and Gemini 2.5 Flash up to a 95% coordination ratio. This ablation narrows the claim: the main RCWT cliff is best read as task-budget displacement, not as proof that coordination volume alone causes semantic interference in the original open-ended task. RCWT is therefore a measurement primitive for context-allocation budgeting, not a complete theory of multi-agent benefit or session-level coordination.

As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even the largest context windows. Current methods for effectively diagnosing agent failures load the full trajectory into an LLM's context window, which suffers from attention dilution and fails when agentic traces inevitably exceed context limits. To address this, we introduce SAFARI (Scaling long-horizon Agentic Fault AttRibution via active Investigation), a framework that replaces linear context loading with a tool-augmented diagnostic loop. By equipping LLMs with a specialized toolbox to read and search trajectory segments alongside a persistent Short-Term Memory (STM) for cross-turn reasoning, SAFARI effectively decouples diagnostic accuracy from architectural context limits. Our experiments demonstrate that SAFARI outperforms state-of-the-art results by 20% on the Who&When dataset within a 1M token budget, and by 19% on TRAIL GAIA subset on a 25K token budget. Most significantly, SAFARI maintains a 0.58 precision even when the target fault resides 5x beyond the model's native context window, a scenario where traditional evaluators fail entirely.

AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficiency for non-English text and structural entropy in conversational prompts. Existing approaches act reactively by compressing already-bloated contexts or intervening after failures occur. We introduce a pre-flight, edge-side prompt-rewriting middleware that operates between the developer and the cloud agent. A local Llama 3.2 (3B) model performs cross-lingual translation into English, structural rewriting into a compact task-oriented format, and regex-validated rewrite-with-fallback safeguards to ensure the optimized prompt is never larger than the original. We evaluate on OMH-Polyglot, a multilingual coding benchmark spanning Turkish, Arabic, Chinese, and code-switched specifications. Across three commercial LLM backends, the middleware reduces prompt tokens by 34-47 percent and total tokens by up to 18.8 percent while preserving or improving task accuracy. Ablation studies show that gains arise primarily from the rewriting stage rather than simple function-name extraction. Compared with LLMLingua-2 at matched compression rates, our method consistently achieves superior OckScore performance across all evaluated backends. These results demonstrate that proactive prompt optimization can substantially reduce inference costs without sacrificing coding quality.

Modern deep learning models for forecasting groups of time series rely on increasingly longer observation windows. However, the benefit of increasing the window size is often simply attributed to capturing long-range dependencies, and broader discussion on how global forecasting models leverage input observations has been limited. In this paper, we show that forecasting groups of time series involves two objectives: (i) generative process identification (GPI), i.e., inferring the specific process generating the input sequence, and (ii) conditional forecasting (CF), i.e., predicting future values given input observations. From this perspective, optimal predictions can be interpreted as an average over plausible data-generating processes, weighted by their likelihood given the input window. This suggests another explanation for the benefits of long context windows: they reduce the uncertainty about which specific process is generating the input time series during operation. We prove that even for processes with memory length $P$, an input window size strictly larger than $P$ is necessary to achieve the minimum attainable error. Finally, we show how decoupling GPI and CF can improve computational scalability without compromising accuracy. Experiments on synthetic and real-world data validate our insights and their relevance for designing forecasting architectures.

Context window efficiency is a practical constraint in large language model (LLM)-based developer tools. Paulsen [12] shows that all tested models degrade in accuracy well before their advertised context limits the Maximum Effective Context Window (MECW) which makes context construction a quality problem, not just a cost one. Modern software repositories routinely contain large non-code artifacts compiled datasets, binary model weights, minified JavaScript bundles, and gigabyte-scale log files that overflow the context window and push out task-relevant source code. We present a correctness-aware context hygiene framework: a pre-execution, size-based heuristic filter that intercepts repository scans before tokenization, using only OS-level stat() metadata with sub-millisecond overhead. Semantic retrieval approaches such as RepoCoder, GraphRAG, and AST-based chunking require index construction and query-time inference before any filtering decision is reached. Our framework, by contrast, requires no indexing and operates at <0.01 ms per file decision. Across 10 real open-source repositories (22,046 files, 5 languages), the proposed SizeFilter at θ=1 MB achieves 79.6% (\pm13.2%) mean token reduction at 0.30 ms overhead: the HybridFilter achieves 89.3% (\pm9.0%) the lowest variance of any filter evaluated. A token-density study across 2,688 files confirms a strong linear correlation (Pearson r=0.997, k=0.250 tokens/byte). A limited-scope evaluation (18 tasks, CodeLlama-7B-Instruct) yields 72% file-level accuracy under filtering versus 25% at baseline; hallucination frequency declines from 61% to 17%. All code and data are released for reproducibility.

Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4 games over 500 rounds, expanding accessible history degrades cooperation in 18 of 28 model--game settings, a pattern we term the memory curse. We isolate the underlying mechanism through three analyses. First, lexical analysis of 378,000 reasoning traces associates this breakdown with eroding forward-looking intent rather than rising paranoia. We validate this using targeted fine-tuning as a cognitive probe: a LoRA adapter trained exclusively on forward-looking traces mitigates the decay and transfers zero-shot to distinct games. Second, memory sanitization holds prompt length fixed while replacing visible history with synthetic cooperative records, which restores cooperation substantially, proving the trigger is memory content, not length alone. Finally, ablating explicit Chain-of-Thought reasoning often reduces the collapse, showing that deliberation paradoxically amplifies the memory curse. Together, these results recast memory as an active determinant of multi-agent behavior: longer recall can either destabilize or support cooperation depending on the reasoning patterns it elicits.

We evaluate the long-context retrieval and reasoning capabilities of five frontier large language models with advertised 1M-token context windows on a classical Chinese corpus. Two complementary studies are reported. Test 1 measures single-needle retrieval at 1M tokens of input, with three biographical needles planted at three depths and pairs of real (training-prior-consistent) and altered (training-prior-contradicting) variants to separate genuine in-context retrieval from reliance on memorised training data. Test 2, a follow-up designed to probe whether long-context capability degrades when retrieval requires intermediate reasoning, measures three-hop chain traversal across three context tiers (256K, 512K, and 1M tokens). We find that single-needle retrieval at 1M is essentially solved for the strongest models - Gemini 3.1 Pro, Claude Opus 4.7, and GPT-5.5 each achieve 100% - but that multi-hop performance reveals three distinct decay signatures: a stable regime (Gemini Pro, Claude) maintaining greater than 80% accuracy through 512K with modest degradation at 1M; a late-cliff regime (GPT-5.5, Qwen3.6-plus) collapsing sharply between 512K and 1M; and a smooth-decline regime (DeepSeek V4 Pro) decaying gradually across the entire range. The findings suggest that nominal context-window length is a poor proxy for usable long-context multi-hop capability, and that the sharpest discriminator between current 1M-context flagships is the 512K-to-1M transition.

We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a session accumulates history, CWL keeps the context within budget through graduated, semantically-aware eviction: the agent annotates its trajectory as typed, dependency-linked episodes as work proceeds, and a deterministic, LLM-free policy evicts content in priority order within that structure when a token budget is exceeded. CWL preserves user turns and the exploratory context the agent is actively reasoning over, while aggressively shedding action episodes whose effects are already persisted in the environment, keeping active context near a stable ceiling that also avoids the performance degradation associated with very large prompts. Compared to summarization-based compaction, CWL avoids four well-known limitations: unpredictable lossiness, destruction of causal structure, blocking model cost, and compression-induced hallucination. Compared to recency truncation, CWL is semantically aware: it drops the oldest-and-most-recoverable content according to the dependency graph rather than oldest-in-time regardless of relevance. We describe the annotation protocol, the episode graph, the eviction policy, and the token-accounting loop, and evaluate CWL on long-horizon agentic benchmarks: a single agent session completing 89 sequential tasks across 80 million tokens with no measurable degradation in task accuracy relative to per-task isolated sessions

Retrieval-Augmented Generation (RAG) systems depend critically on document chunking quality for retrieving relevant context. Fixed chunking segments documents into uniform units irrespective of semantics or user intent, producing a precision-recall trade-off unresolvable by tuning chunk size alone. Semantic and agentic methods partially address these limitations but do not integrate user queries at the chunking stage. We present Query-Adaptive Semantic Chunking (QASC), which dynamically constructs chunks by integrating queries into segmentation through three mechanisms: cosine similarity scoring between sentence and query embeddings to identify seed sentences, contextual window expansion around seeds to preserve coherence, and chunk-level score aggregation to ensure holistic relevance. We evaluate QASC on 100 technical documents across 200 queries spanning four types, comparing against fixed chunking at five granularities, recursive splitting, semantic chunking, and agentic chunking. QASC achieves an F1-score of 0.85, a relative improvement of 18-27% over fixed chunking and 8-12% over semantic and agentic alternatives. Ablation studies confirm each component contributes meaningfully. Human evaluation by three annotators (Cohen kappa = 0.82) corroborates that QASC produces more relevant and coherent chunks than existing methods.

We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction. Although recent object-centric feed-forward methods produce robust, high-quality reconstructions, they still lag behind dense-view optimization in recovering fine-grained texture and appearance. We show that expanding the context window -- by substantially increasing the number of active object and image tokens -- narrows this gap and enables high-fidelity 3D object reconstruction and inverse rendering. To scale effectively, we adapt native sparse attention for 3D reconstruction with three key contributions: (1) an efficient coarse-to-fine pipeline that focuses computation on informative regions by predicting sparse high-resolution residuals; (2) a 3D-aware spatial routing mechanism that establishes accurate 2D-3D correspondences using explicit geometric distances rather than standard attention scores; and (3) a custom block-aware sequence-parallel strategy with an All-gather-KV protocol to balance dynamic, sparse workloads across GPUs. As a result, LSRM handles 20x more object tokens and >2x more image tokens than prior state-of-the-art (SOTA) methods. Extensive evaluations on standard novel-view synthesis benchmarks show substantial gains over the current SOTA, yielding >2.4dB higher PSNR and >40% lower LPIPS. Furthermore, when extending LSRM to inverse rendering, qualitative and quantitative evaluations on widely used benchmarks demonstrate consistent improvements in texture and geometry details, achieving an LPIPS that matches or exceeds that of SOTA dense-view optimization methods. Code and model weights are available on our project page.

Single Image Super-Resolution (SISR) is a fundamental computer vision task that aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) input. Transformer-based methods have achieved remarkable performance by modeling long-range dependencies in degraded images. However, their feature-intensive attention computation incurs high computational cost. To improve efficiency, most existing approaches partition images into fixed groups and restrict attention within each group. Such group-wise attention overlooks the inherent asymmetry in token similarities, thereby failing to enable flexible and token-adaptive attention computation. To address this limitation, we propose the Individualized Exploratory Transformer (IET), which introduces a novel Individualized Exploratory Attention (IEA) mechanism that allows each token to adaptively select its own content-aware and independent attention candidates. This token-adaptive and asymmetric design enables more precise information aggregation while maintaining computational efficiency. Extensive experiments on standard SR benchmarks demonstrate that IET achieves state-of-the-art performance under comparable computational complexity.