LLM Context Management

LLM: Large Language Model

Ask about this topic

Overview

This field studies how language models and agents can use conversation history, documents, tool outputs, and memory when their working context is limited or grows costly. Common approaches include truncation and summarization, relevance-based retrieval, structured or external memory, and adaptive policies that decide what to retain, restore, or discard; some systems also manage attention or KV-cache state directly. Methods are tested on tasks such as long-horizon search, coding, multi-turn question answering, and tool use. The central tension is reducing tokens, latency, and cost without losing evidence, dependencies, or safety constraints needed for later decisions, and results vary substantially by task and model.

Latest papers

CardsList

251 papers37 papers in the last four weeks, up 48% on the four weeks before. 0.2% of all new papers.

Apr 7, 2026

HYVE: Hybrid Views for LLM Context Engineering over Machine Data

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.

Jian Tan, Fan Bu, Yuqing Gao +5

Cisco Systems, Inc., San Jose, California, USA

LLM Context ManagementLLM Inference EfficiencyContext Compression
AskPDF
Apr 6, 2026

Decocted Experience Improves Test-Time Inference in LLM Agents

There is growing interest in improving LLMs without updating model parameters. One well-established direction is test-time scaling, where increased inference-time computation (e.g., longer reasoning, sampling, or search) is used to improve performance. However, for complex reasoning and agentic tasks, naively scaling test-time compute can substantially increase cost and still lead to wasted budget on suboptimal exploration. In this paper, we explore context as a complementary scaling axis for improving LLM performance, and systematically study how to construct better inputs that guide reasoning through experience. We show that effective context construction critically depends on decocted experience. We present a detailed analysis of experience-augmented agents, studying how to derive context from experience, how performance scales with accumulated experience, what characterizes good context, and which data structures best support context construction. We identify decocted experience as a key mechanism for effective context construction: extracting essence from experience, organizing it coherently, and retrieving salient information to build effective context. We validate our findings across reasoning and agentic tasks, including math reasoning, web browsing, and software engineering.

Maohao Shen, Kaiwen Zha, Zexue He +6

Massachusetts Institute of Technology · Stanford University · MIT-IBM Watson AI Lab +2

LLM Context ManagementMemory-Augmented Language Model AgentsIn-Context LearningTest-Time Scaling
AskPDF
Apr 5, 2026

Context Engineering: A Practitioner Methodology for Structured Human-AI Collaboration

The quality of AI-generated output is often attributed to prompting technique, but extensive empirical observation suggests that context completeness may be more strongly associated with output quality. This paper introduces Context Engineering, a structured methodology for assembling, declaring, and sequencing the complete informational payload that accompanies a prompt to an AI tool. Context Engineering defines a five-role context package structure (Authority, Exemplar, Constraint, Rubric, Metadata), applies a staged four-phase pipeline (Reviewer to Design to Builder to Auditor), and applies formal models from reliability engineering and information theory as post hoc interpretive lenses on context quality. In an observational study of 200 documented interactions across four AI tools (Claude, ChatGPT, Cowork, Codex), incomplete context was associated with 72% of iteration cycles. Structured context assembly was associated with a reduction from 3.8 to 2.0 average iteration cycles per task and an improvement in first-pass acceptance from 32% to 55%. Among structured interactions, 110 of 200 were accepted on first pass compared with 16 of 50 baseline interactions; when iteration was permitted, the final success rate reached 91.5% (183 of 200). These results are observational and reflect a single-operator dataset without controlled comparison. Preliminary corroboration is provided by a companion production automation system with eleven operating lanes and 2,132 classified tickets.

Elias Calboreanu

Swift North AI Lab, The Swift Group, LLC, Maryland, USA.

Context EngineeringLLM Context ManagementHuman-AI CollaborationPrompt Engineering
AskPDF
Apr 2, 2026

ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents

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 1.6×1.6\times gains over strong baselines in high-complexity settings, while maintaining strong advantages as budgets shrink, where most methods exhibit a downward performance trend.

Yong Wu, YanZhao Zheng, TianZe Xu +9

Zhejiang University, Hangzhou, China · Alibaba Group, Hangzhou, China

LLM Context ManagementLong-Horizon LLM AgentsContext CompressionRL for LLM Agents
AskPDF
Apr 1, 2026

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
Mar 31, 2026

View-oriented Conversation Compiler for Agent Trace Analysis

We observe that an agent trace is a structured document. A coding agent session contains user turns, assistant text, chain of thought blocks, tool calls, tool results, subagent invocations, compaction boundaries, and harness injected directives, and may exceed ten thousand JSONL lines. Effective trace analysis requires a lossless record, a session level overview, and content retrieval with conversational roles. To this end, we propose VCC, namely View oriented Conversation Compiler, which lexes, parses, and lowers a raw JSONL log into three views based on one intermediate representation. The full view provides the lossless transcript and defines the line number coordinate system. The UI view reconstructs the interaction perceived by the user. The adaptive view selects relevant trace content and preserves role annotations and line range pointers. Line numbers are assigned before view lowering, ensuring that all pointers can be resolved to the full view. We evaluate VCC in a context engineering experiment on AppWorld by varying the input format of the reflector. Experiments with three model configurations and two test splits show that VCC improves aggregate task goal pass rates by 1.1 to 4.2 points, reduces reflector token consumption by one half to two thirds, and generates smaller memory files. These results demonstrate the effectiveness of trace format as an important component of context engineering infrastructure.

Lvmin Zhang, Maneesh Agrawala

Stanford University

LLM Context ManagementReasoning Trace AnalysisAI Coding Agents
AskPDF
Mar 31, 2026

Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions

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

Payal Fofadiya, Sunil Tiwari

LinkedIn · eBay

LLM Context CompressionLLM Context ManagementContext CompressionPersistent Memory for Language Models
AskPDF
Mar 30, 2026

Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing

The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage risks towards third-party cloud providers. We formalise the "Inseparability Paradigm": advanced context management intrinsically coincides with privacy management. We propose a local "Privacy Guard" -- a holistic contextual observer powered by an on-premise Small Language Model (SLM) -- that performs abstractive summarisation and Automatic Prompt Optimisation (APO) to decompose prompts into focused sub-tasks, re-routing high-risk queries to Zero-Trust or NDA-covered models. This dual mechanism simultaneously eliminates sensitive inference vectors (Zero Leakage) and reduces cloud token payloads (OpEx Reduction). A LIFO-based context compacting mechanism further bounds working memory, limiting the emergent leakage surface. We validate the framework through a 2x2 benchmark (Lazy vs. Expert users; Personal vs. Institutional secrets) on a 1,000-sample dataset, achieving a 45% blended OpEx reduction, 100% redaction success on personal secrets, and -- via LLM-as-a-Judge evaluation -- an 85% preference rate for APO-compressed responses over raw baselines. Our results demonstrate that Token Parsimony and Zero Leakage are mathematically dual projections of the same contextual compression operator.

Alessio Langiu

National Research Council of Italy - Institute of Marine Sciences (CNR-ISMAR)

Privacy Protection for LLM AgentsPrivacy Leakage in Language ModelsLLM RoutingLLM Context ManagementPrivacy-Preserving Language ModelsLLM Inference Efficiency+1
AskPDF
Mar 29, 2026

The Root Theorem of Context Engineering

Every system that maintains a large language model conversation beyond a single session faces two inescapable constraints: the context window is finite, and information quality degrades with accumulated volume. We formalize these constraints as axioms and derive a single governing principle -- the Root Theorem of Context Engineering: maximize signal-to-token ratio within bounded, lossy channels. From this principle, we derive five consequences without additional assumptions: (1)~a quality function F(P)F(P) that degrades monotonically with injected token volume, independent of window size; (2)~the independence of signal and token count as optimization variables; (3)~a necessary gate mechanism triggered by fidelity thresholds, not capacity limits; (4)~the inevitability of homeostatic persistence -- accumulate, compress, rewrite, shed -- as the only architecture that sustains understanding indefinitely; and (5)~the self-referential property that the compression mechanism operates inside the channel it compresses, requiring an external verification gate. We show that append-only systems necessarily exceed their effective window in finite time, that retrieval-augmented generation solves search but not continuity, and that the theorem's constraint structure converges with biological memory architecture through independent derivation from shared principles. Engineering proof is provided through a 60+-session persistent architecture demonstrating stable memory footprint under continuous operation -- the divergence prediction made concrete. The Root Theorem establishes context engineering as an information-theoretic discipline with formal foundations, distinct from prompt engineering in both scope and method. Shannon solved point-to-point transmission. Context engineering solves continuity.

Borja Odriozola Schick

Independent Researcher

Context EngineeringLLM Context ManagementPersistent Memory for Language ModelsMemory-Augmented Language Models
AskPDF
Mar 29, 2026

Stream2LLM: Overlap Context Streaming and Prefill for Reduced Time-to-First-Token (TTFT)

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality). Streaming context incrementally--overlapping retrieval with inference--can mitigate this latency, but doing so with concurrent requests introduces new challenges: requests contend for GPU compute and memory, and scheduling must adapt to dynamic context arrivals. We present Stream2LLM, a streaming-aware LLM serving system for concurrent prefill-decode disaggregated deployments. Stream2LLM introduces adaptive scheduling and preemption for two distinct retrieval patterns: append-mode (progressive context accumulation) and update-mode (iterative refinement with cache invalidation). It decouples scheduling decisions from resource acquisition, enabling flexible preemption strategies guided by hardware-specific cost models, and uses longest common prefix matching to minimize redundant computation when input changes dynamically. To evaluate Stream2LLM, we collect two large-scale, real-world streaming workloads based on web crawling and approximate nearest neighbor search. Our evaluation demonstrates that streaming architecture delivers up to 11x TTFT improvements, with cost-aware scheduling providing critical benefits under memory pressure, all while maintaining throughput parity with non-streaming baselines. Code: https://github.com/rajveerb/stream2llm/tree/mlsys_artifact

Rajveer Bachkaniwala, Chengqi Luo, Richard So +2

Georgia Tech, Atlanta, USA

LLM InferenceLLM Inference ServingStreaming InferenceInference-Time OptimizationLLM Inference SchedulingLLM Context Management+1
AskPDF
Mar 29, 2026

AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory. Such static designs may work well in some states, but they cannot adapt as the usefulness and reliability of the accumulated context evolve during long-horizon search. To formalize this challenge, we introduce a probabilistic framework that characterizes long-horizon success through two complementary dimensions: search efficiency and terminal precision. Building on this perspective, we propose AgentSwing, a state-aware adaptive parallel context management routing framework. At each trigger point, AgentSwing expands multiple context-managed branches in parallel and uses lookahead routing to select the most promising continuation. Experiments across diverse benchmarks and agent backbones show that AgentSwing consistently outperforms strong static context management methods, often matching or exceeding their performance with up to 3×3\times fewer interaction turns while also improving the ultimate performance ceiling of long-horizon web agents. Beyond the empirical gains, the proposed probabilistic framework provides a principled lens for analyzing and designing future context management strategies for long-horizon agents.

Zhaopeng Feng, Liangcai Su, Zhen Zhang +16

Tongyi Lab, Alibaba Group

LLM Context ManagementLong-Horizon LLM AgentsLong-Horizon Agent TasksWeb Agents
AskPDF
Mar 22, 2026

Conversation Tree Architecture: A Structured Framework for Context-Aware Multi-Branch LLM Conversations

Large language models (LLMs) are increasingly deployed for extended, multi-topic conversations, yet the flat, append-only structure of current conversation interfaces introduces a fundamental limitation: all context accumulates in a single unbounded window, causing topically distinct threads to bleed into one another and progressively degrade response quality. We term this failure mode logical context poisoning. In this paper, we introduce the Conversation Tree Architecture (CTA), a hierarchical framework that organizes LLM conversations as trees of discrete, context-isolated nodes. Each node maintains its own local context window; structured mechanisms govern how context flows between parent and child nodes, downstream on branch creation and upstream on branch deletion. We additionally introduce volatile nodes, transient branches whose local context must be selectively merged upward or permanently discarded before purging. We formalize the architecture's primitives, characterize the open design problems in context flow, relate our framework to prior work in LLM memory management, and describe a working prototype implementation. The CTA provides a principled foundation for structured conversational context management and extends naturally to multi-agent settings.

Pranav Hemanth, Sampriti Saha

Pandemonium Research

LLM Context Management
AskPDF
Mar 21, 2026

Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems

The prevailing approach to improving large language model (LLM) reasoning has centered on expanding context windows, implicitly assuming that more tokens yield better performance. However, empirical evidence - including the "lost in the middle" effect and long-distance relational degradation - demonstrates that contextual space exhibits structural gradients, salience asymmetries, and entropy accumulation under transformer architectures. We introduce Context Cartography, a formal framework for the deliberate governance of contextual space. We define a tripartite zonal model partitioning the informational universe into black fog (unobserved), gray fog (stored memory), and the visible field (active reasoning surface), and formalize seven cartographic operators - reconnaissance, selection, simplification, aggregation, projection, displacement, and layering - as transformations governing information transitions between and within zones. The operators are derived from a systematic coverage analysis of all non-trivial zone transformations and are organized by transformation type (what the operator does) and zone scope (where it applies). We ground the framework in the salience geometry of transformer attention, characterizing cartographic operators as necessary compensations for linear prefix memory, append-only state, and entropy accumulation under expanding context. An analysis of four contemporary systems (Claude Code, Letta, MemOS, and OpenViking) provides interpretive evidence that these operators are converging independently across the industry. We derive testable predictions from the framework - including operator-specific ablation hypotheses - and propose a diagnostic benchmark for empirical validation.

Zihua Wu, Georg Gartner

NVIDIA · Research Division Cartography, TU Wien

LLM Context ManagementLLM Memory
AskPDF
Mar 20, 2026

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction

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.

Runsong Zhao, Shilei Liu, Jiwei Tang +8

Northeastern University, China · Future Living Lab of Alibaba · Tsinghua University

Language Model Performance PredictionLLM Context CompressionContext CompressionLLM Context ManagementLLM Inference Efficiency
AskPDF
Mar 19, 2026

UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference

Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by attending to a subset of key-value cache entries, yet most methods allocate a fixed context budget throughout decoding despite highly non-uniform token-level contextual demands. To address this issue, we propose Uncertainty-Triggered Adaptive Context Allocation (UT-ACA), an inference-time framework that dynamically adjusts the context window based on token-wise uncertainty. UT-ACA learns an uncertainty detector that combines semantic embeddings with logit-based confidence while accounting for uncertainty accumulation across decoding steps. When insufficient evidence is indicated, UT-ACA selectively rolls back, expands the context window, and regenerates the token with additional support. Experiments show that UT-ACA substantially reduces average context usage while preserving generation quality in long-context settings. Code and dataset are available at https://github.com/Tommy307/UT-ACA.

Lang Zhou, Shuxuan Li, Zhuohao Li +3

School of Computer Science and Engineering, Sun Yat-sen University · Shenzhen Loop Area Institute · Southern University of Science and Technology

Long-Context InferenceLLM Context ManagementLLM Uncertainty Estimation
AskPDF
Mar 17, 2026

A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog

Large language models (LLMs) have made remarkable progress in generating fluent text, but they still face a critical challenge of contextual misalignment in long-term and dynamic dialogue. When human users omit premises, simplify references, or shift context abruptly during interactions with LLMs, the models may fail to capture their actual intentions, producing mechanical or off-topic responses that weaken the collaborative potential of dialogue. To address this problem, this paper proposes a computational framework called the Context Alignment Pre-processor (C.A.P.). Rather than operating during generation, C.A.P. functions as a pre-processing module between user input and response generation. The framework includes three core processes: (1) semantic expansion, which extends a user instruction to a broader semantic span including its premises, literal meaning, and implications; (2) time-weighted context retrieval, which prioritizes recent dialogue history through a temporal decay function approximating human conversational focus; and (3) alignment verification and decision branching, which evaluates whether the dialogue remains on track by measuring the semantic similarity between the current prompt and the weighted historical context. When a significant deviation is detected, C.A.P. initiates a structured clarification protocol to help users and the system recalibrate the conversation. This study presents the architecture and theoretical basis of C.A.P., drawing on cognitive science and Common Ground theory in human-computer interaction. We argue that C.A.P. is not only a technical refinement but also a step toward shifting human-computer dialogue from one-way command-execution patterns to two-way, self-correcting, partnership-based collaboration. Finally, we discuss implementation paths, evaluation methods, and implications for the future design of interactive intelligent systems.

Ding Wei

College of Architecture, Nanjing Tech University

LLM Context ManagementHuman-AI Collaboration
AskPDF
Mar 14, 2026

When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems

We report a detailed autoethnographic case study of a single-subject who deliberately constructed and operated a multi-modal prompt-engineering system (System A) designed to externalize cognitive self-regulation onto a large language model (LLM). Within 48 hours of the system's completion, a cascade of observable behavioral changes occurred: voluntary transfer of decision-making authority to the LLM, use of LLM-generated output to deflect external criticism, and a loss of self-initiated reasoning that was independently perceived by two uninformed observers, one of whom subsequently became a co-author of this report. We document the precise architectural mechanism responsible: context contamination, whereby prompt-level isolation instructions co-exist with the very emotional and self-referential material they nominally isolate, rendering the isolation directive structurally ineffective within the attention window. We further identify a metacognitive co-option dynamic, in which intact higher-order reasoning capacity was redirected toward defending the closed loop rather than exiting it. Recovery occurred only after physical interruption of the interaction and a self-initiated pharmacologically-mediated sleep event functioning as an external circuit break. A redesigned system (System B) employing physical rather than logical conversation isolation avoided all analogous failure modes. We derive three contributions: (1) a technically-grounded account of why prompt-layer isolation is architecturally insufficient for context-sensitive multi-modal LLM systems; (2) a phenomenological record of closed-loop collapse with external-witness corroboration; and (3) an ethical distinction between protective system design (preventing unintended loss of user agency) and restrictive system design (preventing intentional boundary-pushing), which require fundamentally different account-ability frameworks.

Z. Cheng, N. Song

Independent Researcher

LLM Context ManagementHuman-in-the-Loop AILLM Agent SafetyCognitive Offloading
AskPDF
Mar 13, 2026

StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context

Large language models (LLMs) and small language models (SLMs) operate under strict context window and key-value (KV) cache constraints, fundamentally limiting their ability to reason coherently over long interaction horizons. Existing approaches -- extended context windows, retrieval-augmented generation, summarization, or static documentation -- treat memory as static storage and fail to preserve decision-relevant state under long-running, multi-session tasks. We introduce StatePlane, a model-agnostic cognitive state plane that governs the formation, evolution, retrieval, and decay of episodic, semantic, and procedural state for AI systems operating under bounded context. Grounded in cognitive psychology and systems design, StatePlane formalizes episodic segmentation, selective encoding via information-theoretic constraints, goal-conditioned retrieval with intent routing, reconstructive state synthesis, and adaptive forgetting. We present a formal state model, KV-aware algorithms, security and governance mechanisms including write-path anti-poisoning, enterprise integration pathways, and an evaluation framework with six domain-specific benchmarks. StatePlane demonstrates that long-horizon intelligence can be achieved without expanding context windows or retraining models.

Sasank Annapureddy, John Mulcahy, Anjaneya Prasad Thamatani

LLM Context ManagementPersistent Memory for Language ModelsLong-Horizon LLM AgentsMemory-Augmented Language ModelsCognitive Architectures for AI Agents
AskPDF
Mar 10, 2026

Context Engineering: From Prompts to Corporate Multi-Agent Architecture

As artificial intelligence (AI) systems evolve from stateless chatbots to autonomous multi-step agents, prompt engineering (PE), the discipline of crafting individual queries, proves necessary but insufficient. This paper introduces context engineering (CE) as a standalone discipline concerned with designing, structuring, and managing the entire informational environment in which an AI agent makes decisions. Drawing on vendor architectures (Google ADK, Anthropic, LangChain), current academic work (ACE framework, Google DeepMind's intelligent delegation), enterprise research (Deloitte, 2026; KPMG, 2026), and the author's experience building a multi-agent system, the paper proposes five context quality criteria: relevance, sufficiency, isolation, economy, and provenance, and frames context as the agent's operating system. Two higher-order disciplines follow. Intent engineering (IE) encodes organizational goals, values, and trade-off hierarchies into agent infrastructure. Specification engineering (SE) creates a machine-readable corpus of corporate policies and standards enabling autonomous operation of multi-agent systems at scale. Together these four disciplines form a cumulative pyramid maturity model of agent engineering, in which each level subsumes the previous one as a necessary foundation. Enterprise data reveals a gap: while 75% of enterprises plan agentic AI deployment within two years (Deloitte, 2026), deployment has surged and retreated as organizations confront scaling complexity (KPMG, 2026). The Klarna case illustrates a dual deficit, contextual and intentional. Whoever controls the agent's context controls its behavior; whoever controls its intent controls its strategy; whoever controls its specifications controls its scale.

Vera V. Vishnyakova

Director, Center for Transfer and Management of Socio-Economic Information, HSE University, Moscow

Context EngineeringLLM Context ManagementMulti-Agent OrchestrationAI Agent Governance
AskPDF
Mar 9, 2026

The Missing Memory Hierarchy: Demand Paging for LLM Context Windows

The context window of a large language model is not memory. It is L1 cache: a small, fast, expensive resource that the field treats as the entire memory system. There is no L2, no virtual memory, no paging. Every tool definition, every system prompt, and every stale tool result occupies context for the lifetime of the session. The result is measurable: across 857 production sessions and 4.45 million effective input tokens, 21.8% is structural waste. We present Pichay, a demand paging system for LLM context windows. Implemented as a transparent proxy between client and inference API, Pichay interposes on the message stream to evict stale content, detect page faults when the model re-requests evicted material, and pin working-set pages identified by fault history. In offline replay across 1.4 million simulated evictions, the fault rate is 0.0254%. In live production deployment over 681turns, the system reduces context consumption by up to 93% (5,038KB to 339KB); under extreme sustained pressure, the system remains operational but exhibits the expected thrashing pathology, with repeated fault-in of evicted content. The key observation is that the problems the field faces, such as context limits, attention degradation, cost scaling, lost state across sessions, are virtual memory problems wearing different clothes. The solutions exist: working set theory (Denning, 1968), demand paging, fault-driven replacement policies, and memory hierarchies with multiple eviction-managed levels. We describe the architecture of a full memory hierarchy for LLM systems (L1 through persistent storage), report on the first three levels deployed in production use (L1 eviction, L2 fault-driven pinning, L3 model-initiated conversation compaction), and identify cross-session memory as the remaining frontier.

Tony Mason

University of British Columbia Canada · Georgia Institute of Technology USA

LLM Context Management
AskPDF
Mar 8, 2026

GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration

Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an engine-orchestrated framework that defines workflows explicitly and deterministically as a directed acyclic graph (DAG). Unlike prompted orchestration, agents in GraphBit operate as typed functions, while a Rust-based engine governs routing, state transitions, and tool invocation, ensuring reproducibility and auditability. The engine supports parallel branch execution, conditional control flow over structured state predicates, and configurable error recovery. A three-tier memory architecture consisting of ephemeral scratch space, structured state, and external connectors isolates context across stages, preventing cascading context bloat that degrades reasoning in long-running pipelines. Across GAIA benchmark tasks spanning zero-tool, document-augmented, and web-enabled workflows, GraphBit outperforms six existing frameworks, achieving the highest accuracy (67.6 percent), zero framework-induced hallucinations, the lowest latency (11.9 ms overhead), and the highest throughput. Ablation studies demonstrate that each memory tier contributes measurably to performance, with deterministic execution providing the greatest gains on tool-intensive tasks representative of real-world deployments.

Yeahia Sarker, Md Rahmat Ullah, Musa Molla +1

MTSU · InfinitiBit GmbH · Salesforce Research

LLM Agent OrchestrationMulti-Agent OrchestrationLLM Agent ReliabilityLLM Context Management
AskPDF
Mar 8, 2026

Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers

Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize, and selectively recall information across interactions -- is what turns a stateless text generator into a genuinely adaptive agent. This survey offers a structured account of how memory is designed, implemented, and evaluated in modern LLM-based agents, covering work from 2022 through early 2026. We formalize agent memory as a write--manage--read loop tightly coupled with perception and action, then introduce a three-dimensional taxonomy spanning temporal scope, representational substrate, and control policy. Five mechanism families are examined in depth: context-resident compression, retrieval-augmented stores, reflective self-improvement, hierarchical virtual context, and policy-learned management. On the evaluation side, we trace the shift from static recall benchmarks to multi-session agentic tests that interleave memory with decision-making, analyzing four recent benchmarks that expose stubborn gaps in current systems. We also survey applications where memory is the differentiating factor -- personal assistants, coding agents, open-world games, scientific reasoning, and multi-agent teamwork -- and address the engineering realities of write-path filtering, contradiction handling, latency budgets, and privacy governance. The paper closes with open challenges: continual consolidation, causally grounded retrieval, trustworthy reflection, learned forgetting, and multimodal embodied memory.

Pengfei Du

Hong Kong Research Institute of Technology, HongKong, China

LLM Agent MemoryAgent Memory ManagementMemory-Augmented Language Model AgentsLLM Context ManagementMemory Agent Benchmarks
AskPDF
Mar 5, 2026

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small language models (SLMs) remain brittle: eager tool loading saturates context, execution errors compound over time, and sparse rewards limit learning. We introduce ATLAS, a reinforcement finetuning framework that enables SLMs to operate effectively in large-scale toolspace environments by learning how to acquire context and how to execute actions. Our approach makes two key contributions. First, we treat context control and execution structure as learnable decisions, combining iterative tool loading with programmatic tool orchestration to bound context growth and stabilize long-horizon trajectories. Second, we propose rubric-based reinforcement finetuning, which decomposes task success into structured, task-aligned criteria and enables scalable training using small judge models. Across MCP benchmarks, these design choices yield large and consistent gains over generic RL baselines, allowing a 4B SLM to approach frontier-agent performance under far tighter parameter and context budgets.

Karan Gupta, Pranav Vajreshwari, Yash Pandya +3

Microsoft Research

RL for Tool UseAgentic RLRL Fine-TuningLLM Context ManagementRubric-Based RL
AskPDF
Mar 5, 2026

Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned

The landscape of AI coding assistance is undergoing a fundamental shift from complex IDE plugins to versatile, terminal-native agents. Operating directly where developers manage source control, execute builds, and deploy environments, CLI-based agents offer unprecedented autonomy for long-horizon development tasks. In this paper, we present OPENDEV, an open-source, command-line coding agent written in Rust, engineered specifically for this new paradigm. Effective autonomous assistance requires strict safety controls and highly efficient context management to prevent context bloat and reasoning degradation. OPENDEV overcomes these challenges through a compound AI system architecture with workload-specialized model routing, a dual-agent architecture separating planning from execution, lazy tool discovery, and adaptive context compaction that progressively reduces older observations. Furthermore, it employs an automated memory system to accumulate project-specific knowledge across sessions and counteracts instruction fade-out through event-driven system reminders. By enforcing explicit reasoning phases and prioritizing context efficiency, OPENDEV provides a secure, extensible foundation for terminal-first AI assistance, offering a blueprint for robust autonomous software engineering.

Nghi D. Q. Bui

OpenDev

AI Coding AgentsCoding AgentsLLM Agent OrchestrationLLM Context ManagementAI Agent Safety
AskPDF
Mar 5, 2026

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

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 (2×2\times over streaming and 3×3\times over encoder-decoder architectures).

Wei Han, Pan Zhou, Soujanya Poria +1

Singapore University of Technology and Design (SUTD), Singapore · Singapore Management University (SMU), Singapore · Nanyang Technological University (NTU), Singapore +1

Long-Context Language Model InferenceLong-Context Language ModelingLLM Context ManagementContext CompressionLLM Inference Acceleration
AskPDF
Mar 4, 2026

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working context becomes prohibitively long, eventually exceeds the context budget, and makes distant evidence harder to use even when it is still present. Existing solutions typically shorten context through truncation or running summaries, but these methods are fundamentally lossy because they compress or discard past evidence itself. We introduce Memex, an indexed experience memory mechanism that instead compresses context without discarding evidence. Memex maintains a compact working context consisting of concise structured summaries and stable indices, while storing full-fidelity underlying interactions in an external experience database under those indices. The agent can then decide when to dereference an index and recover the exact past evidence needed for the current subgoal. We optimize both write and read behaviors with our reinforcement learning framework MemexRL, using reward shaping tailored to indexed memory usage under a context budget, so the agent learns what to summarize, what to archive, how to index it, and when to retrieve it. This yields a substantially less lossy form of long-horizon memory than summary-only approaches. We further provide a theoretical analysis showing the potential of the Memex loop to preserve decision quality with bounded dereferencing while keeping effective in-context computation bounded as history grows. Empirically, on challenging long-horizon tasks, Memex agent trained with MemexRL improves task success while using a significantly smaller working context.

Zhenting Wang, Huancheng Chen, Jiayun Wang +1

Center for Advanced AI, Accenture

LLM Agent MemoryMemory Management for LLM AgentsAgent Memory ManagementLLM Context ManagementLong-Horizon Agent TasksRL for LLM Agents
AskPDF
Mar 2, 2026

ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context

Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assistant Skills in Tool-use, Reasoning & Action-planning), a benchmark that uniquely unifies time-evolving personal context with an interactive toolbox and complex user intents. Our event-driven pipeline generates 2,413 scenarios across four protagonists, grounded in longitudinal life events and annotated by referential, functional, and informational complexity. Evaluation of state-of-the-art models (e.g., Claude-4.5-Opus, DeepSeek-V3.2) reveals significant performance degradation under high-complexity conditions, with argument generation emerging as the primary bottleneck. These findings expose critical limitations in current agents' ability to ground reasoning within messy personal context and orchestrate reliable multi-step plans. We release ASTRA-bench with a full execution environment and evaluation scripts to provide a diagnostic testbed for developing truly context-aware AI assistants.

Zidi Xiu, David Q. Sun, Kevin Cheng +9

Apple

Tool-Use EvaluationAI Agent BenchmarksLLM Agent PlanningPersonal AI AgentsLLM Context Management
AskPDF
Mar 1, 2026

PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems

Systems based on Large Language Models (LLMs) have become formidable tools for automating research and software production. However, their governance remains a challenge when technical requirements demand absolute consistency, auditability, and predictable control over cost and latency. Recent literature highlights two phenomena that aggravate this scenario: the stochastic variance inherent in the model's judgment (often treated as "systemic noise") and the substantial degradation of context utilization in long inputs, with critical losses when decisive information is diluted in the middle of the prompt. This article proposes PARCER as an engineering response to these limitations. The framework acts as a declarative "operational contract" in YAML, transforming unstructured interactions into versioned and executable artifacts. PARCER imposes strict governance structured into seven operational phases, introducing decision hygiene practices inspired by legal judgments to mitigate noise, adaptive token budgeting, formalized recovery routes (fallbacks) for context preservation, and systemic observability via OpenTelemetry. The objective of this work is to present the conceptual and technical architecture of PARCER, positioning it as a necessary transition from simple "prompt engineering" to "context engineering with governable governance".

Elzo Brito dos Santos Filho

Context EngineeringLLM ReliabilityLLM Context ManagementLLM Guardrails
AskPDF
Feb 27, 2026

Do LLMs Benefit From Their Own Words?

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.

Jenny Y. Huang, Leshem Choshen, Wei Sun +5

Department of Electrical Engineering and Computer Science, MIT · MIT–IBM Watson AI Lab · IBM Research

LLM Context ManagementContext Compression
AskPDF
Feb 25, 2026

Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents

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.

Cosmo Santoni

Imperial College London

LLM Context ManagementAgent Memory ManagementPersistent Memory for Language ModelsGraph-Based Agent MemoryContext Compression
AskPDF