LLM Context Management

LLM: Large Language Model

Ask about this topic

Momentum

23 papers in the last four weeks, up 92% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 156

All topics
CardsList
May 14, 2026cs.AI

A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency

Large language models often suffer from fact loss, timeline confusion, persona drift, and reduced stability during long-range interaction, especially under high-noise knowledge bases, context clearing, and cross-model transfer. To address these issues, we introduce ARPM, an external temporal memory governance framework for long-term dialogue. ARPM separates static knowledge memory from dynamic dialogue experience memory and combines vector retrieval, BM25, RRF fusion, dual-temporal reranking, chronological evidence reading, and a controlled analysis protocol for evidence verification and answer binding. Unlike approaches that encode persona consistency into model weights or rely only on long context, ARPM treats continuity as a traceable, auditable, and transferable governance problem. Using engineering logs, we conduct three experiments. First, in a 50-round question-answering setting, we compare signal-to-noise ratios of 1:5 and 1:200+, and distinguish CSV auto-judgment from manual review. Under 1:5, CSV recall accuracy is 54.0%, while manual review raises it to 100.0%. Under 1:200+, the values are 44.0% and 80.0%. These results show that automatic rules can underestimate recall after supporting evidence enters the prompt. Second, ablation results show that dialogue history retrieval is necessary for recent continuity: disabling it reduces strict accuracy from 100% to 66.7%, and disabling BM25 reduces it to 80.0%, indicating that pure semantic retrieval is insufficient for correction and tracing. Third, under a 5.1-million-character noise substrate, periodic context clearing, and multi-model handoff, ARPM maintains semantic continuity, boundary continuity, and persona consistency, while exposing limits caused by weak protocol compliance. These findings show that long-term persona consistency can be decomposed into governable components and evaluated in a white-box manner.

Zhao Yang, Wang Huan, Li Yingshuo +2

Changchun Kelaile Technology Co., Ltd, Qinglong Road, Luyuan District, Changchun, 130000, Jilin, China. · School of Electronic Information, Zhongshan Institute, University of Electronic Science and Technology of China, No. 1 Xueyuan Road,2026 Zhongshan, 528402, Guangdong, China.

Memory-Augmented Language ModelsPersona ConsistencyPersistent Memory for Language ModelsLong-Term Conversational MemoryLLM Context Management
AskPDF
May 14, 2026cs.CL

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring

Extending the context window of large language models typically requires training on sequences at the target length, incurring quadratic memory and computational costs that make long-context adaptation expensive and difficult to reproduce. We propose EndPrompt, a method that achieves effective context extension using only short training sequences. The core insight is that exposing a model to long-range relative positional distances does not require constructing full-length inputs: we preserve the original short context as an intact first segment and append a brief terminal prompt as a second segment, assigning it positional indices near the target context length. This two-segment construction introduces both local and long-range relative distances within a short physical sequence while maintaining the semantic continuity of the training text--a property absent in chunk-based simulation approaches that split contiguous context. We provide a theoretical analysis grounded in Rotary Position Embedding and the Bernstein inequality, showing that position interpolation induces a rigorous smoothness constraint over the attention function, with shared Transformer parameters further suppressing unstable extrapolation to unobserved intermediate distances. Applied to LLaMA-family models extending the context window from 8K to 64K, EndPrompt achieves an average RULER score of 76.03 and the highest average on LongBench, surpassing LCEG (72.24), LongLoRA (72.95), and full-length fine-tuning (69.23) while requiring substantially less computation. These results demonstrate that long-context generalization can be induced from sparse positional supervision, challenging the prevailing assumption that dense long-sequence training is necessary for reliable context-window extension. The code is available at https://github.com/clx1415926/EndPrompt.

Han Tian, Luxuan Chen, Xinran Chen +10

1Nankai University · 2Baidu Inc. · 3Shanghai Jiao Tong University +1

Long-Context Language ModelingLLM Fine-TuningLLM Context Management
AskPDF
May 14, 2026cs.SE

Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints

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.

Shweta Mishra

Independent Researcher

LLM Context ManagementCode Language Models
AskPDF
May 13, 2026cs.AI

Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations

In a long conversation, an LLM may produce a fluent continuation that rests on premises the conversation has already abandoned. Context-manipulation attacks exploit precisely this weakness. We address this problem with a runtime verifier. An LLM Interpreter maps each utterance to one or more of eight epistemic operations, and then a symbolic engine applies these operations to a dependency map that records what every claim rests on and whether it still stands. Based on the dependency map, checking whether a continuation is grounded then reduces to a walk over the map, linear in its size and requiring no LLM call. Retraction propagates through the same map with a conflict-free guarantee and flags exactly the conclusions that lose support. Our experiments with five QA models demonstrate substantial improvements in QA accuracy at a low cost per query. On ReviseQA for belief revision and MemoryAgentBench's FactConsolidation split (MemAB-FC), the verifier outperforms a retrieval baseline and raises MemAB-FC single-hop accuracy from 0.460.46--0.950.95 to 0.940.94--0.980.98. With the verifier, even the small 7B model overtakes unaided GPT-4o. When a GPT-4o Interpreter extracts every update from raw text rather than taking the benchmarks' structured updates, the verifier still outperforms the retrieval baseline. Moreover, on MemAB-FC, QA prompts remain compact at 9797--174174 tokens while the full-context baseline reaches 114.5114.5K. Retraction queries take less than a microsecond at 20002000 turns.

Qisong He, Jinwei Hu, Xinmiao Huang +3

School of Computer Science & Informatics, University of Liverpool

Belief RevisionLLM GroundingLLM Answer VerificationReasoning Consistency in Language ModelsLLM ReliabilityLLM Context Management+1
AskPDF
May 11, 2026cs.CV

Personal Visual Context Learning in Large Multimodal Models

As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the evolution of these models into true personal assistants hinges on visual personalization: the ability to reason over visual information unique to the wearer. We formalize this capability as Personal Visual Context Learning (Personal VCL), the prompt-time capability of using user-specific visual context to resolve personalized queries. To systematically evaluate this, we present Personal-VCL-Bench, a comprehensive benchmark capturing the personal visual world across persons, objects, and behaviors. Our analysis of frontier LMMs identifies a profound context utilization gap, revealing that the mechanisms for leveraging visual evidence, as well as aggregating multiple visual observations, remain critically understudied. Motivated by these findings, we propose the Agentic Context Bank, a strong inference-time baseline that structures a user's visual context into a self-refining memory bank and employs query-adaptive evidence selection. Our baseline approach consistently improves over standard context prompting regimes across tasks and evaluated backbones, demonstrating a practical path towards future personalized LMMs.

Zihui Xue, Ami Baid, Sangho Kim +2

The University of Texas at Austin

Vision-Language ModelsMultimodal Large Language ModelsLLM Context ManagementMemory-Augmented Language Model Agents
AskPDF
May 11, 2026cs.SE

On Problems of Implicit Context Compression for Software Engineering Agents

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.

Kirill Gelvan, Igor Slinko, Felix Steinbauer +3

JetBrains Research · Technical University of Munich, Germany

Software Engineering AgentsLong-Horizon LLM AgentsLLM Context ManagementContext Compression
AskPDF
May 11, 2026cs.CL

SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution

Large Language Model (LLM)-based agents (e.g., OpenClaw) increasingly rely on reusable skill libraries to solve artifact-rich tasks such as document-centric workflows and data-intensive analysis. As these libraries grow, a few works have attempted to study the Retrieval-Augmented Execution (RAE), which often first retrieves some external skills and other knowledge, then compiles the context using retrieved skills, and finally executes the task. Existing works mainly focus on optimizing skill retrieval and task execution, and they pay little attention to how to effectively organize the selected skill evidence in a form that is compact, grounded, and immediately usable for the downstream executors to complete tasks. To fill this gap, we propose SkillRAE, a two-stage RAE approach focusing on skill-based context compilation, which consists of the offline and online stages. Specifically, in the offline indexing stage, it builds a multi-level skill graph over skill communities, skills, and reusable subunits, for capturing their relationships. In the online retrieval stage, it first performs skill-ranked retrieval with selected-subunit evidence export in the graph, and then applies rescue-aware compact compilation to recover the key evidence. Together, these components compile a coarse-ranked skill set into a task-specific context that is compact, grounded, and immediately usable. Experiments on two public benchmarks show that SkillRAE achieves a significant improvement over baselines for RAE. For example, on SkillsBench, it achieves an improvement of 11.7% over the SOTA method. Ablation studies further show that our context compilation is crucial, instead of a mere prompt addition.

Xiangcheng Meng, Shu Wang, Yixiang Fang

The Chinese University of Hong Kong, Shenzhen

Agentic RetrievalLLM Agent Skill RetrievalLLM AgentsLLM Context Management
AskPDF
May 10, 2026cs.CL

Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs

Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns, leading to inaccurate responses. In this paper, we stress-test the multi-turn understanding of LLMs and study the following two sub-tasks: (1) detecting whether the user pivots or refines in the current turn, and (2) shortlisting relevant context from previous turns. To this end, we construct synthetic benchmarks based on real-world datasets from varied domains, as to simulate context shifts of different levels of difficulty. We then evaluate the zero-shot performance of ten LLMs (open-weight, closed-source and reasoning), and demonstrate that only some reasoning and strongly instructed LLMs are accurate in detecting pivots; open-weight LLMs struggle with the task and frequently carry stale context even with explicit cues; and all models suffer from a position bias. Based on the results, we discuss key takeaways for improving long-term robustness in multi-turn capabilities for LLMs.

Aditya Sinha, Harald Steck, Vito Ostuni +1

Netflix Inc. · Los Gatos, CA, USA

LLM EvaluationMulti-Turn Dialogue EvaluationLLM Context Management
AskPDF
May 8, 2026cs.AI

Why Retrying Fails: Context Contamination in LLM Agent Pipelines

When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the next attempt and elevating the per-step error rate beyond the base level. This context-contaminated restart phenomenon is widely observed in practice yet entirely lacks formal treatment. We introduce the Context-Contaminated Restart Model (CCRM): a chain of T tool-call steps, each failing with base rate epsilon_0; after any failed attempt, the subsequent attempt operates in contaminated context with elevated error rate epsilon_1 > epsilon_0. Under this model we derive five main results. (R1) An exact closed-form formula for P(succeed in at most K attempts). (R2) A cascade-overhead theorem giving the additional attempts Delta K incurred by contamination versus the clean-restart baseline. (R3) An optimal budget-allocation theorem identifying the pipeline depth T* that maximises success probability for a fixed total budget B=KT; we prove the closed form T* = sqrt(B * log(1/(1-epsilon_1)) / log(1/(1-epsilon_0))), with K*=B/T*. (R4) An information-theoretic lower bound via Le Cam's method showing K_CCRM is tight up to O(1). (R5) A clean-restart dominance theorem quantifying the exact benefit of context-clearing before retry. We validate CCRM on real SWE-bench Verified data: the IID model overestimates pass@3 by 17.4 percentage points (98.6% vs. 81.2%), while CCRM fits with error less than 0.001, implying a cascade ratio of epsilon_1/epsilon_0 = 7.1. Monte Carlo experiments confirm all theoretical predictions.

Zhanfu Yang

Department of Computer Science, Rutgers University, Piscataway, NJ 08854, USA

LLM Context ManagementLLM Agent Reliability
AskPDF
May 8, 2026cs.AI

Learning CLI Agents with Structured Action Credit under Selective Observation

Command line interface (CLI) agents are emerging as a practical paradigm for agent-computer interaction over evolving filesystems, executable command line programs, and online execution feedback. Recent work has used reinforcement learning (RL) to learn these interaction abilities from verifiable task feedback, yet few methods exploit the native structured attributes of CLI actions as learning signals. Beyond this underused action structure, CLI learning also couples two bottlenecks for coding agents. First, the agent must identify task-relevant evidence in a large codebase from partial observations. Second, sparse terminal rewards must be assigned to the actions that shape a long multi-turn trajectory. We study these bottlenecks through shell-driven information extraction and file editing tasks. For selective observation, we introduce σσ-Reveal, an inference-time mechanism that selects token-budgeted context for the same CLI. For credit assignment, we propose Action Advantage Assignment (A3\mathrm{A}^3), a native agentic RL method that preserves the algorithmic complexity of standard agentic RL. A3\mathrm{A}^3 constructs turn-level advantages from episode-level relative feedback, abstract syntax tree (AST) based action sub-chain residuals, and tree-level trajectory margins. To further evaluate this problem setting, we construct ShellOps, a verifiable dataset suite covering CLI tasks in repository environments.

Haoyang Su, Ying Wen

Fudan University · Shanghai Innovation Institute · Shanghai Jiao Tong University

Computer-Use AgentsCredit Assignment in RLAI Agent BenchmarksSparse-Reward RLLLM Context ManagementRL for Tool Use
AskPDF
May 7, 2026cs.AI

The Context Gathering Decision Process: A POMDP Framework for Agentic Search

Large Language Model (LLM) agents are deployed in complex environments -- such as massive codebases, enterprise databases, and conversational histories -- where the relevant state far exceeds their context windows. To navigate these spaces, an agent must iteratively explore the environment to find relevant information. However, without explicit infrastructure, an agent's working memory can degrade into lossy representations of the search state, resulting in redundant work (e.g. repetitive looping) and premature stopping. In this work, we formalize this challenge as the Context Gathering Decision Process (CGDP), a specialized Partially Observable Markov Decision Process, where an agent's objective is to adaptively refine its belief state to isolate the necessary information for a task. We model an LLM's behavior as approximate Thompson Sampling within this CGDP, and introduce a predicate-based method that decomposes an LLM's implicit search into explicit and modular operations. We then derive two plug-and-play interventions for iterative LLM agents: a persistent, predicate-based belief state that bounds context while preserving multi-hop reasoning, and a programmatic exhaustion gate that halts unproductive search without premature stopping. Across four methods and three question-answering domains, we empirically validate that replacing an LLM's implicit state with our CGDP-motivated belief state improves multi-hop reasoning by up to 11.4%11.4\%; while the modular programmatic exhaustion detection saves up to 39%39\% of tokens without any degradation in agent performance. Ultimately, we argue that framing the LLM agent loop as a CGDP can guide the design of modular, non-interfering improvements to agentic search harnesses.

Chinmaya Kausik, Adith Swaminathan, Nathan Kallus

University of Michigan · Netflix

Agentic SearchLLM AgentsPartially Observable Markov Decision ProcessesMulti-Hop ReasoningLLM Context Management
AskPDF
May 7, 2026cs.CL

Can LLMs Take Retrieved Information with a Grain of Salt?

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a limitation with real consequences in high-stakes domains like medicine and finance. We evaluate eight LLMs on their context-certainty obedience, measuring how well they adjust responses to match expressed context certainty. Our analysis reveals systematic limitations: LLMs struggle to recall prior knowledge after observing an uncertain context, misinterpret expressed certainties, and overtrust complex contexts. To address these, we propose an interaction strategy combining prior reminders, certainty recalibration, and context simplification. This approach reduces obedience errors by 25% on average, without modifying model weights, demonstrating the efficacy of interaction design in enhancing LLM reliability. Our contributions include a principled evaluation metric, empirical insights into LLMs' uncertainty handling, and a portable strategy to improve context-certainty obedience across diverse LLMs.

Behzad Shayegh, Mohamed Osama Ahmed, Fred Tung +1

RBC Borealis

Retrieval-Augmented GenerationLLM EvaluationLLM Uncertainty EstimationLanguage Model RobustnessLLM Context Management
AskPDF
May 6, 2026cs.AI

From History to State: Constant-Context Skill Learning for LLM Agents

Large language model (LLM) agents are increasingly used to operate browsers, files, code and tools, making personal assistants a natural deployment target. Yet personal agents face a privacy-cost-capability tension: cloud models execute multi-step workflows well but expose sensitive intermediate context to external APIs, while local models preserve privacy but remain less reliable. Both settings also pay repeatedly for long skill prompts and growing histories. We propose constant-context skill learning, a context-to-weights framework for recurring agent workflows: reusable procedures are learned in lightweight task-family modules, while inference conditions only on the current observation and a compact state block. A deterministic tracker renders this state block from task progress and supplies aligned subgoal rewards, so each module can be trained with step-level SFT and refined through online RL. Across ALFWorld, WebShop, and SciWorld, our agents achieve strong performance across Qwen3-4B, Qwen3-8B and Llama-3.1-8B. With Qwen3-8B, SFT+RL reaches 89.6% unseen success on ALFWorld, 76.8% success on WebShop, and 66.4% unseen success on SciWorld. They match or exceed strong published agent-training results while reducing prompt tokens per turn by 2--7×\times relative to controlled ReAct prompting baselines, showing that procedural context can be moved from prompts into weights.

Haoyang Xie, Xinyuan Wang, Yancheng Wang +2

School of Computing and Augmented Intelligence, Arizona State University

LLM Agent Skill LearningLLM Agent TrainingLLM Context ManagementRL for LLM Agents
AskPDF
May 6, 2026cs.AI

LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents

Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can overwhelm the agent, increasing costs and the risk of errors. We propose that effective context management should be adaptive: parts of the agent's trajectory are maintained at different levels of detail depending on their current relevance to the task. To operationalize this principle, we introduce Context-ReAct, a general agentic paradigm for elastic context orchestration that integrates reasoning, context management, and tool use in a unified loop. Context-ReAct provides five atomic operations: Skip, Compress, Rollback, Snippet and Delete, which allow the agent to dynamically reshape its working context, preserving important evidence, summarizing resolved information, discarding unhelpful branches, and controlling context size. We prove that the Compress operator is expressively complete, while the other specialized operators provide efficiency and fidelity guarantees that reduce generation cost and hallucination risk. Building on this paradigm, we develop LongSeeker, a long-horizon search agent fine-tuned from Qwen3-30B-A3B on 10k synthesized trajectories. Across four representative search benchmarks, LongSeeker achieves 61.5% on BrowseComp and 62.5% on BrowseComp-ZH, substantially outperforming Tongyi DeepResearch (43.2% and 46.7%) and AgentFold (36.2% and 47.3%). These results highlight the potential of adaptive context management, showing that agents can achieve more reliable and efficient long-horizon reasoning by actively shaping their working memory.

Yijun Lu, Rui Ye, Yuwen Du +3

Shanghai Jiao Tong University

Web Search AgentsTool-Using AgentsLong-Horizon LLM AgentsLLM Context Management
AskPDF
May 5, 2026cs.AI

When Context Hurts: The Crossover Effect of Knowledge Transfer on Multi-Agent Design Exploration

The prevailing assumption in agent orchestration is that more context is better. We test this on multi-agent software design across 10 tasks, 7 context-injection conditions, and over 2,700 runs, and find a crossover effect: the same artifact type improves design exploration on some tasks (up to 20×\times tradeoff coverage) and actively degrades it on others (up to 46% reduction). On several tasks, an irrelevant document performs as well as or better than every relevant artifact. The direction is predicted by a single measurable variable--baseline exploration without context--with Pearson r=−0.82r = -0.82 (p<0.001p < 0.001). Probing the mechanism by manipulating convergence pressure through prompt design reveals two distinct regimes: convergence driven by training data priors (natural) responds to artifact disruption, while convergence driven by explicit instructions (induced) does not. The implication is that context injection should be conditional, not universal: one no-context trial is a cheap diagnostic that predicts whether knowledge artifacts will help or hurt a given task.

Saranyan Vigraham

Meta

Software Engineering AgentsLLM Agent OrchestrationLLM Context Management
AskPDF
May 4, 2026cs.AI

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to move a settled loop somewhere else, and whether that move lasts. We study this in 30-step recursive loops by separating the model from the context-update rule: append, replace, and dialog updates expose different histories to the same generator. The main result is that persistent redirection in append-mode recursive loops is memory-policy-conditioned. Under a 12,000-character tail clip, destination-coherent persistence plateaus near 16 percent and retained source-basin escape near 36 percent at dose 400; neither crosses 50 percent. Under a full-history protocol, retained source-basin escape crosses 50 percent near 400 tokens and saturates at 75-80 percent by 1,500 tokens; destination-coherent persistence first reaches 0.50 near 1,500 tokens (Wilson 95 percent CI [0.41, 0.61]). A four-step falsification battery (heterogeneity control, granularity sweep with hierarchical macro-merge, transition-entropy diagnostic, and long-horizon trajectory continuation) recasts the high-dose destination-coherent dip as a finite-horizon, endpoint-definition-sensitive feature rather than a stable structural asymmetry. Half the canonical magnitude is endpoint timing; the residual drops 73 percent from -0.143 at step 29 to -0.039 at step 79 under the frozen canonical cluster basis, bootstrap interval straddling zero. Replace-mode raw switching is near-saturated under the default protocol but largely reflects state-reset overwrite: insert-mode probes drop it to 12-32 percent. We report 37 experiments on gpt-4o-mini with within-vendor replication on gpt-4.1-nano. Recursive-loop evaluations should distinguish transient movement from durable escape, subtract stochastic floors, and treat context-update rules as safety-relevant design choices.

Pawel Kaplanski

Kaplanski AI Lab · Kaplanski Ai Lab

Language Model RobustnessLLM Context Management
AskPDF
May 3, 2026cs.AI

A Language for Describing Agentic LLM Contexts

Large language models are increasingly used within larger systems ("LLM agents"). These make a sequence of LLM calls, each call providing the LLM with a combination of instructions, observations, and interaction history. The design of the encoded information and its structure play a central role in the quality of the resulting system, leading to efforts spent on context engineering. It is therefore critical to communicate the composition of the LLM context in a system, and how it evolves over time. Yet, no standard exists for doing so: context construction is typically conveyed through informal prose, ad hoc diagrams, or direct inspection of code, none of which precisely capture how a prompt evolves across interaction steps or how two context representation strategies differ. To remedy this, we introduce the Agentic Context Description Language (ACDL), a language for specifying the structure and dynamics of LLM input contexts in a precise, readable, and standard manner, along with visualizations. ACDL provides constructs for specifying context aspects such as role message sequences, dynamic content, time-indexed references, and conditional or iterative structure, capturing the full architecture of a prompt independently of any particular implementation. ACDL diagrams can be hand drawn on a whiteboard, or written in formal language which can then be rendered. We describe the language, demonstrate it by documenting several existing systems and their variants, and encourage the community to adopt it for describing LLM systems context, both in day-to-day communication and in papers. Tooling, examples and documentation are available at www.acdlang.org.

Noga Peleg Pelc, Gal A. Kaminka, Yoav Goldberg

Dept. of Computer Science and AI Bar-Ilan University

LLM PromptingLLM AgentsLLM Context Management
AskPDF
May 1, 2026cs.CL

Beyond Compaction: Structured Context Eviction for Long-Horizon Agents

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

Andrew Semenov, Svyatoslav Dorofeev

Kiz8

Long-Horizon LLM AgentsLLM Context ManagementAgent Memory Management
AskPDF
May 1, 2026cs.CL

Context Recycling for Long-Horizon LLM Inference

Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due to context window limitations and inefficient token usage. We introduce ContextForge, a system for context recycling that maintains task-relevant information across turns by combining structured query generation, external memory retrieval, and controlled synthesis. The system enables efficient reuse of prior computation without relying on full context replay, reducing token overhead while preserving answer quality. We evaluate ContextForge using a 15-turn conversational benchmark that tests multi-turn reasoning, back-references, and domain shifts across structured healthcare queries. Compared to a baseline agent using identical underlying models, ContextForge demonstrates improved consistency and reduced token consumption, while maintaining comparable response accuracy. These results suggest that context recycling provides a practical approach for extending LLM capabilities in long-horizon tasks without requiring larger context windows or model retraining. Code and evaluation artifacts are available at https://github.com/Betanu701/ContextForge.

Derek Thomas

Independent Researcher · contextforge

LLM Inference EfficiencyLong-Context Language Model InferenceLLM Context ManagementMemory-Augmented Language Model Agents
AskPDF
May 1, 2026cs.CL

Budget-Aware Routing for Long Clinical Text

A key challenge for large language models is token cost per query and overall deployment cost. Clinical inputs are long, heterogeneous, and often redundant, while downstream tasks are short and high stakes. We study budgeted context selection, where a subset of document units is chosen under a strict token budget so an off-the-shelf generator can meet fixed cost and latency constraints. We cast this as a knapsack-constrained subset selection problem with two design choices, unitization that defines document segmentation and selection that determines which units are kept. We propose \textbf{RCD}, a monotone submodular objective that balances relevance, coverage, and diversity. We compare sentence, section, window, and cluster-based unitization, and introduce a routing heuristic that adapts to the budget regime. Experiments on MIMIC discharge notes, Cochrane abstracts, and L-Eval show that optimal strategies depend on the evaluation setting. Positional heuristics perform best at low budgets in extractive tasks, while diversity-aware methods such as MMR improve LLM generation. Selector choice matters more than unitization, with cluster-based grouping reducing performance and other schemes behaving similarly. ROUGE saturates for LLM summaries, while BERTScore better reflects quality differences. We release our code at https://github.com/stone-technologies/ACL_budget_paper.

Khizar Qureshi, Geoffrey Martin, Yifan Peng

MIT, Cambridge, MA · Cornell University, Ithaca, NY · Weill Cornell Medicine, New York, NY

Submodular OptimizationLong-Context Language Model InferenceClinical NLPLLM Context Management
AskPDF
Apr 29, 2026cs.CL

CL-bench Life: Can Language Models Learn from Real-Life Context?

Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life.

Shihan Dou, Yujiong Shen, Chenhao Huang +35

Hunyuan Team, Tencent · Fudan University

LLM EvaluationLLM GroundingIn-Context LearningLLM Context Management
AskPDF
Apr 27, 2026cs.CL

Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination

Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We propose a scalable Enterprise Deep Research (EDR) architecture to address these failures. Our system (i) decomposes requests into coverage-driven objectives via outline generation with reflection, (ii) localizes context with dependency-guided execution and explicit information sharing, and (iii) enforces evidence-based completion criteria so agents iteratively collect information until sufficiency conditions are met. We evaluate on an internal sales enablement task and the public DeepResearch Bench benchmark, where our proposed system design achieves the strongest overall performance compared with competitive deep-research baselines. The results show that dependency-controlled context and explicit evidence sufficiency criteria reduce premature stopping and improve the consistency and depth of enterprise research outputs.

Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit +5

Salesforce AI Research

Deep Research AgentsLLM Agent OrchestrationEvidence-Grounded GenerationLLM Context Management
AskPDF
Apr 24, 2026cs.CL

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

Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured information that later steps rely on. Recent retrieval-based memory systems surface relevant content but still overlook the causal and logical structure needed for multi-step reasoning. We introduce ContextWeaver, a selective and dependency-structured memory framework that organizes an agent's interaction trace into a graph of reasoning steps and selects the relevant context for future actions. Unlike prior context management approaches, ContextWeaver supports: (1) dependency-based construction and traversal that link each step to the earlier steps it relies on; (2) compact dependency summarization that condenses root-to-step reasoning paths into reusable units; and (3) a lightweight validation layer that incorporates execution feedback. On the SWE-Bench Verified and Lite benchmarks, ContextWeaver improves performance over a sliding-window baseline in pass@1, while reducing reasoning steps and token usage. Our observations suggest that modeling logical dependencies provides a stable and scalable memory mechanism for LLM agents that use tools.

Yating Wu, Yuhao Zhang, Sayan Ghosh +4

UT Austin · AWS AI Labs

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

Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows

The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on stateless, eager schema injection imposes a hidden per-turn overhead the MCP Tax or Tools Tax that practitioner reports place between roughly 10k and 60k tokens in typical multi-server deployments. This payload inflates the key-value cache, is associated with reasoning degradation as context utilization approaches published fracture points around 70%, and turns token budgets into a recurring operational cost. We introduce Tool Attention, a middleware-layer mechanism that generalizes the "Attention Is All You Need" paradigm from self-attention over tokens to gated attention over tools. Tool Attention combines (i) an Intent Schema Overlap (ISO) score from sentence embeddings, (ii) a state-aware gating function enforcing preconditions and access scopes, and (iii) a two-phase lazy schema loader that keeps a compact summary pool in context and promotes full JSON schemas only for top-k gated tools. We evaluate on a simulated 120-tool, six-server benchmark whose per-server token counts are calibrated to public audits of real MCP deployments. In this simulation, Tool Attention directly reduces measured per-turn tool tokens by 95.0% (47.3k -> 2.4k) and raises effective context utilization (a token-ratio quantity) from 24% to 91%. End-to-end figures for task success, latency, cost, and reasoning quality are reported as projections derived from the measured token counts combined with published deployment telemetry; they are not measured on live LLM agents, and we mark projected values explicitly throughout. Taken together, the results support a simple thesis: protocol-level efficiency, not raw context length, is a binding constraint on scalable gentic systems. The code for this work is accessible at https://github.com/asadani/tool-attention

Anuj Sadani, Deepak Kumar

Gated AttentionLLM Tool UseTool-Using Language AgentsLLM Context Management
AskPDF
Apr 21, 2026cs.AI

CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable LLM Interactions

Reliability in large language model (LLM) systems is typically framed as a function of model capability. We challenge this by demonstrating that reliability is significantly influenced by \emph{inference-time control} -- the computational layer governing task framing and context selection. We introduce \emph{CogniConsole}, an architectural instantiation that externalizes this control into a structured interface combining programmatic coordination with bounded prompt-based reasoning. Through \emph{controllability-oriented probes} (N=489N=489) in a multi-step interactive environment, we show that increasing structural scaffolding -- from unstructured to fully scaffolded -- \textbf{systematically reduces output variance and failure rates under a fixed model architecture}. Our results indicate that many observed failure modes, such as context drift and inconsistent constraint adherence, arise from under-specified control rather than insufficient capability. This work provides an empirical basis for treating inference-time control as a first-class abstraction, opening new directions for designing and evaluating LLM systems beyond scaling alone.

Vanessa Figueiredo, Wilter Franceschi

Orbital Sea Regina, SK, Canada

AI Agent ReliabilityLanguage Model-Based ControlLLM ReliabilityLLM Context ManagementLLM Agent Reliability
AskPDF
Apr 21, 2026cs.AI

Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction

We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed agents that advance shared tasks without waiting for user prompts. The architecture rests on three mutually reinforcing mechanisms. Write-time context assembly precomputes enriched typed attributes via Groker agents, assembling interaction context as a deterministic pure function of graph state; context blocks are byte-identical across turns between semantic changes, enabling near-100% KV-cache reuse. Composable sandboxed wisdom programs form a governed library of LM-generated imperative programs declaratively wired to goal types via typed stream relations, composed via phase ordering, and executed at interaction time without further LM calls. Proactive goal stream state machines drive conversations toward terminal states by inspecting graph state and emitting structured interaction content (option arrays, governance affordances, clarification prompts) without awaiting user input. We prove six formal results: the Context Stability Theorem, bounding per-turn LM cost as a function of semantic change rate; a Program Composition Correctness Theorem; a Declarative Wiring Soundness Theorem; the Proactive Dominance Theorem, proving proactive agents weakly dominate reactive agents on expected turns-to-terminal-state; Coordination Overhead Elimination and Quality Preservation, establishing Pareto improvements in multi-participant goal chats; and a Cross-Platform Vote Consistency Theorem. Implemented in the open-source Qbix / Safebox / Safebots stack.

Gregory Magarshak

Qbix, Inc. & Intercoin, Inc. · New York, USA · Also with IE University NYC.

LLM Agent OrchestrationProactive AssistanceAI Agent GovernanceConversational AgentsLLM Context ManagementAgentic AI
AskPDF
Apr 18, 2026cs.CL

LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations

Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered Archival aNd Temporal Episodic Retrieval Network), a lightweight memory layer that proactively archives every conversation turn and restores relevant details after compaction via hybrid retrieval -- requiring zero LLM calls and adding fewer than 25ms of latency per turn. On 94 real multi-turn conversations (1,894 ground-truth facts, human-validated at kappa=0.81), LANTERN-Rerank recovers 78.3% of verifiable facts lost to compaction, significantly outperforming a faithful reimplementation of MemGPT's LLM-driven extraction and multi-query search pipeline (72.4%; Wilcoxon p<0.0001, 95% CI [+3.1, +8.6] pp, d=0.43) at a fraction of the inference cost. Even without the reranker, base LANTERN matches or exceeds this LLM-driven baseline (p=0.005) using zero LLM calls. When four production LLMs answer fact-bearing questions using LANTERN-restored context, accuracy improves by 8.4 percentage points on average (Wilcoxon p<0.05 for each model individually), demonstrating that the recovered context is useful across diverse model architectures. We release the full evaluation framework -- paired significance tests, failure analysis, fact-type stratification, and compaction robustness analysis -- to support reproducibility and future work.

Rahul Subramani

Cisco Systems, Inc.

Memory-Augmented Language ModelsPersistent Memory for Language ModelsLong-Term Conversational MemoryLLM Context Management
AskPDF
Apr 18, 2026cs.CL

GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)

Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for decision-making. At the same time, useful experience gained from tasks is often lost across episodes. We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget. We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: context information density maximization. GA implements this through four closely connected components: a minimal atomic tool set that keeps the interface simple, a hierarchical on-demand memory that only shows a small high-level view by default, a self-evolution mechanism that turns verified past trajectories into reusable SOPs and executable code, and a context truncation and compression layer that maintains information density during long executions. Across task completion, tool use efficiency, memory effectiveness, self-evolution, and web browsing, GA consistently outperforms leading agent systems while using significantly fewer tokens and interactions, and it continues to evolve over time. Project: https://github.com/lsdefine/GenericAgent

Jiaqing Liang, Jinyi Han, Weijia Li +15

Advantage AI Agent Lab (A3 Lab)

Tool-Augmented Language Model AgentsLLM Agent MemoryLLM Agent Skill LearningLong-Horizon LLM AgentsLLM Context ManagementSelf-Evolving Agents
AskPDF
Apr 16, 2026cs.CL

Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)

The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflict between the LLMs' inherent stochasticity (generative, non-deterministic nature) and the analytical requirement for consistency. The LLM inconsistency, coupled with the noisy nature of chaotic modern datasets, renders sentiment predictions too volatile for strategic business decisions. To resolve this, we present a Syntactic & Semantic Context Assessment Summarization (SSAS) framework for establishing context. Context established by SSAS functions as a sophisticated data pre-processing framework that enforces a bounded attention mechanism on LLMs. It achieves this by applying a hierarchical classification structure (Themes, Stories, Clusters) and an iterative Summary-of-Summaries (SoS) based context computation architecture. This endows the raw text with high-signal, sentiment-dense prompts, that effectively mitigate both irrelevant data and analytical variance. We empirically evaluated the efficacy of SSAS, using Gemini 2.0 Flash Lite, against a direct-LLM approach across three industry-standard datasets - Amazon Product Reviews, Google Business Reviews, Goodreads Book Reviews - and multiple robustness scenarios. Our results show that our SSAS framework is capable of significantly improving data quality, up to 30%, through a combination of noise removal and improvement in the estimation of sentiment prediction. Ultimately, consistency in our context-estimation capabilities provides a stable and reliable evidence base for decision-making.

Sharookh Daruwalla, Nitin Mayande, Shreeya Verma Kathuria +2

1Tellagence Inc.∗ · 2Villanova School of Business, Villanova University† · 3Maseeh College of Engineering and Computer Science, Portland State University‡

Sentiment AnalysisLanguage Model RobustnessLLM Context Management
AskPDF
Apr 1, 2026cs.LG

Reasoning Shift: How Context Silently Shortens LLM Reasoning

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting phenomenon: reasoning models tend to produce much shorter reasoning traces (up to 74%) for the same problem under different context conditions compared to the traces produced when the problem is presented in isolation. A finer-grained analysis reveals that this compression is associated with a decrease in self-verification and uncertainty management behaviors, such as double-checking. Importantly, we show that even when additional self-checks are forced, their efficiency depends not only on the content of the reasoning traces, but also on the presence of redundant context. We hope our findings draw additional attention to both the robustness of reasoning models and the problem of context management for LLMs.

Gleb Rodionov, Roman Garipov, George Yakushev

Yandex · HSE University

Language Model RobustnessLLM Context ManagementLLM ReasoningLarge Reasoning Models
AskPDF