Neural Paging: Learning Context Management Policies for Turing-Complete Agents

• URL: http://arxiv.org/abs/2603.02228v1
• Date: Wed, 11 Feb 2026 22:35:08 GMT
• Title: Neural Paging: Learning Context Management Policies for Turing-Complete Agents
• Abstract summary: We introduce textitNeural Paging, a hierarchical architecture that decouples symbolic reasoning from information resource management.<n>We provide theoretical analysis showing that, under bounded context window size$K$, Neural Paging reduces the complexity of long-horizon reasoning from quadratic $O(N2)$ to $O(N cdot K2)$.
• Score: 9.896253083170066
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The proof that Large Language Models (LLMs) augmented with external read-write memory constitute a computationally universal system has established the theoretical foundation for general-purpose agents. However, existing implementations face a critical bottleneck: the finite and costly Context Window, which functions not as infinite memory but as a scarce semantic cache. In this work, we introduce \textit{Neural Paging}, a hierarchical architecture that decouples symbolic reasoning from information resource management. We formulate the \textit{Context Paging Problem (CPP)} and propose a lightweight, differentiable \textit{Page Controller} designed to approximate ``Semantic Belady's Optimality'' -- retaining tokens with high future utility under explicit assumptions on access patterns. We provide theoretical analysis showing that, under bounded context window size~$K$, Neural Paging reduces the asymptotic complexity of long-horizon reasoning from quadratic $O(N^2)$ to $O(N \cdot K^2)$, and we derive a robustness bound (Theorem~4) that quantifies competitive-ratio degradation under policy-dependent access with bounded sensitivity. We validate these bounds on synthetic paging traces, confirming that the theoretical guarantees hold and identifying significant slack that motivates learned policies.

Related papers

• Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework [2.007262412327553]
  We introduce ReLIT, a hybrid framework for deep, semantically grounded implicit reasoning.<n>We show that ReLIT can be scaled efficiently through recurrent depth rather than parameter width.<n>These results demonstrate that reasoning capability can be scaled efficiently through recurrent depth rather than parameter width.
  arXiv  Detail & Related papers  (2026-08-08T12:50:51Z)
• Theoretical Foundations of $\max$@$k$ Reinforcement Learning [21.43014756831114]
  We provide a theoretical study of the $max$@$k$ learning problem in finite-horizon reinforcement learning.<n>We show that optimizing the $max$@$k$ objectives is fundamentally different from standard expected-return objectives.<n>We also show that learning $max$@$k$-optimal policies is statistically harder than standard reinforcement learning.
  arXiv  Detail & Related papers  (2026-07-20T11:11:55Z)
• The Root Theorem of Context Engineering [0.0]
  We formalize constraints as axioms and derive a single governing principle -- the Root Theorem of Context Engineering.<n>We show that append-only systems necessarily exceed their effective window in finite time.<n>We show that the theorem's constraint structure converges with biological memory architecture.
  arXiv  Detail & Related papers  (2026-03-29T20:41:58Z)
• On Multi-Step Theorem Prediction via Non-Parametric Structural Priors [50.16583672681106]
  In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL)<n>We propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference.<n>Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models.
  arXiv  Detail & Related papers  (2026-03-05T06:08:50Z)
• Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning (Extended Version) [49.462399222747024]
  We propose a novel framework for the logical specification of non-Markovian rewards in Decision Processes (MDPs) with large state spaces.<n>Our approach leverages Linear Temporal Logic Modulo Theories over finite traces (LTLfMT)<n>We introduce a method based on reward machines and Hindsight Experience Replay (HER) to translate first-order logic specifications and address reward sparsity.
  arXiv  Detail & Related papers  (2026-02-05T22:11:28Z)
• CoLT: Reasoning with Chain of Latent Tool Calls [31.228763375347608]
  Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs)<n>We propose CoLT, a novel framework that implements latent reasoning as tool calls''
  arXiv  Detail & Related papers  (2026-02-04T06:12:53Z)
• Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents [0.0]
  We introduce textbfProject Ariadne, a novel XAI framework to audit the causal integrity of agentic reasoning.<n>Unlike existing interpretability methods that rely on surface-level textual similarity, Project Ariadne performs textbfhard interventions ($do$-calculus) on intermediate reasoning nodes.<n>Our empirical evaluation of state-of-the-art models reveals a persistent textitFaithfulness Gap.
  arXiv  Detail & Related papers  (2026-01-05T18:05:29Z)
• Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space [56.37266873329401]
  Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density.<n>We propose $textbfDynamic Large Concept Models (DLCM)$, a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts from tokens to a compressed concept space where reasoning is more efficient.
  arXiv  Detail & Related papers  (2025-12-31T04:19:33Z)
• FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution [3.4666771782038652]
  Large language models (LLMs) owe much of their stellar performance to expansive input contexts, yet such verbosity inflates monetary costs, carbon footprint, and inference-time latency.<n>We introduce FrugalPrompt, a novel prompt compression framework for LLMs, which retains only the most semantically significant tokens.<n>We evaluate the approach across four NLP tasks: Sentiment Analysis, Commonsense QA, Summarization, and Mathematical Reasoning.
  arXiv  Detail & Related papers  (2025-10-18T10:22:13Z)
• POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization [28.771942726400084]
  We propose POT (Prompt-Only OverThinking), a black-box attack framework that employs iterative optimization to generate semantically natural adversarial prompts.<n>PoT achieves superior performance compared to other methods.
  arXiv  Detail & Related papers  (2025-08-23T16:27:42Z)
• Neural Expectation Operators [2.1756081703276]
  This paper introduces textbfMeasure Learning, a paradigm for modeling ambiguity via non-linear expectations.<n>We define Neural Expectation Operators as solutions to Backward Differential Equations (BSDEs) whose drivers are parameterized by neural networks.<n>We provide constructive methods for enforcing key axiomatic properties, such as convexity, by architectural design.
  arXiv  Detail & Related papers  (2025-07-13T06:19:28Z)
• Bound by semanticity: universal laws governing the generalization-identification tradeoff [8.437463955457423]
  We show that finite-resolution similarity is a fundamental emergent informational constraint, not merely a toy-model artifact.<n>These results provide an exact theory of the generalization-identification trade-off and clarify how semantic resolution shapes the representational capacity of deep networks and brains alike.
  arXiv  Detail & Related papers  (2025-06-01T15:56:26Z)
• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks [63.35819388164267]
  We present a framework to tackle the memory explosion problem using memory replay techniques. PDGNNs with Topology-aware Embedding Memory (TEM) significantly outperform state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-01-24T03:03:17Z)
• Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction [54.06292969184476]
  We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Our approach employs semantic loss which captures the precise meaning of a logical sentence. With a focus on low-data regimes, we show that semantic loss outperforms the baselines by a wide margin.
  arXiv  Detail & Related papers  (2021-03-20T00:16:29Z)
• Learning Implicitly with Noisy Data in Linear Arithmetic [94.66549436482306]
  We extend implicit learning in PAC-Semantics to handle intervals and threshold uncertainty in the language of linear arithmetic. We show that our implicit approach to learning optimal linear programming objective constraints significantly outperforms an explicit approach in practice.
  arXiv  Detail & Related papers  (2020-10-23T19:08:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.