Cognitive Computing and Networks

Latest papers

• A Mathematical Theory of Pragmatic Information

  Kai Niu, Ping Zhang · 18 September 2026

  We propose a mathematical theory of pragmatic information that connects communication, control, and decision-making. Its central notion is the isoteleia mapping, which formalizes equifinality: distinct semantic paths that lead to the same optimal action are treated as pragmatically equivalent. This …

• Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning

  Cai Ke, Xinghao Chen, Xiaoyu Shen, Keyu Chen, Siyu An, Junnan Dong, Ruifeng Xu, Ruizhi Qiao, Xing Sun · 17 September 2026

  Personalized agents are required to reason over long-term history interactions to infer both explicit preferences and implicit behavioral evidence. While early flat retrieval methods score memory fragments independently and neglect the distributed information, current structured memory frameworks re…

• Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI

  Jiahong Liu, Wenhao Yu, Zexuan Qiu, Menglin Yang, Irwin King · 17 September 2026

  Long-term memory is becoming a core substrate for personalized AI, yet most systems still represent personalization as discrete records in a largely static latent space, accessed under one global similarity notion. For data mining, this creates a mismatch: the evidence is a temporal event stream, wh…

• Phases in a class of associative memories via hidden neurons

  Toshihiro Ota, Masato Taki · 11 September 2026

  Associative memory in the Hopfield network is attractor dynamics in a disordered many-body system, and higher-order and exponential extensions turn its retrieval update into softmax attention. The polynomial and exponential regimes have been analyzed by different methods, with no common architecture…

• InKAN: B-Spline KANs via Truncated Power Form

  Naveen Mysore · 4 September 2026

  Kolmogorov-Arnold Networks (KANs) place learnable B-spline activations on network edges rather than fixed activations on nodes. The standard Cox-de Boor recursion evaluates these activations through $k$ sequential passes for degree-$k$ splines, consuming over 90% of forward-pass time. InKAN replac…

• SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval

  Przemys{\l}aw Stok{\l}osa, Janusz A. Starzyk, Pawe{\l} Raif · 3 September 2026

  This article presents SSAKG 2.0, an open-source software package for constructing and operating Structural Sequential Associative Knowledge Graphs (SSAKGs). An SSAKG represents objects as graph vertices and ordered sequences as structural patterns of graph connections. The resulting sparse graph is …

• Consolidator: Learning Persistent Routed Memory Across Context Boundaries

  Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung · 13 August 2026

  Copying short-term memory (STM) into a slower store can preserve state across a context boundary, but persistence alone does not ensure that the retained state influences subsequent memory access. We test this distinction in a Phasor Memory Network (PMNet) using Consolidator, a shared slot-local ope…

• Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite

  Xiawei Yue, Boran Wang, Xiaoqing Zhang, Shuxin Zheng, Ziwei Zhang · 6 August 2026

  Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue to arrive. Recently, graph memory has been adopted to offer structural organization for multi-hop retrieval and reasoning. However, existing methods …

• SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits

  Kazi Ahmed Asif Fuad, Lizhong Chen · 4 August 2026

  Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions parameterized by multiple basis coefficients. This introduces a source of redundancy that conventional neural-network compression does not directly expose. We present \textbf{SparseKAN}, a unified appr…

• Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Management

  Dariusz Nowak-Nova · 28 July 2026

  The aim of this article is to verify whether integrating large language models (LLMs) with the Retrieval-Augmented Generation (RAG) architecture enables their transformation from standalone generative models into components of cognitive computing infrastructure with enhanced epistemic reliability. T…

• Associative Memory for Non-Stationary Environments: A Self-Sizing Generalization of Hopfield Networks

  Xin Li · 23 June 2026

  The Hopfield network made associative memory (AM) the model system of neural computation, but it solves the problem only for a \emph{stationary} world: a fixed set of memories, stored once into frozen weights. Real environments are non-stationary (e.g., memories arrive over time, drift, recur, and m…

• Indirect Computing Model with Indirect Formal Method

  Xiaohui Zou · 15 June 2026

  This paper,from the perspective of a collaborative intelligent computing system formed by combining human-computer interface and collaborative computing programs, discusses the principles of optimized cloud computing technology supported by the combination of an indirect computing model and an indir…

• A Dynamical Framework for Cognitive Processes Based on Transformations and Semantic Equivalence

  Carlo Cattani, Dioneia Motta Monte-Serrat · 26 May 2026

  This paper proposes a structural and dynamical framework for modeling cognitive processes within a cybernetic perspective. Cognitive states are represented as elements of a state space evolving through an iterative update rule of the form \[ X_{t+1} = \pi\big(F(f(X_t))\big), \] where $f$ des…

• Variational Kolmogorov-Arnold Network

  Francesco Alesiani, Henrik Christiansen, Federico Errica · 8 May 2026

  Kolmogorov-Arnold Networks (KANs) offer a theoretically grounded alternative to multi-layer perceptrons by representing multivariate functions as compositions of univariate basis functions. However, a critical limitation of KANs is the need to manually specify the number of basis functions per layer…

• The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence

  Terry Dorsey, Kevin Huggins · 6 May 2026

  Contemporary artificial intelligence systems achieve strong performance through large-scale parameterization, retrieval augmentation, and training on extensive static corpora. Despite these advances, they continue to face limitations in persistent memory, temporal grounding, provenance, and interpre…

• Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid

  Alessio Donvito, Antonio Lieto · 6 May 2026

  In this paper, we employ the Minimal Cognitive Grid (MCG), a framework created to evaluate the cognitive plausibility of artificial systems, to offer a systematic assessment of leading computational models of analogy and metaphor, including the Structure-Mapping Engine (SME), CogSketch, METCL, and L…

• The Missing Knowledge Layer in Cognitive Architectures for AI Agents

  Micha\"el Roynard (LAAS-OASIS) · 14 April 2026

  The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own persistence semantics. This gap produces a category error: systems apply cognitive decay to factual claims, or treat facts and experiences with ident…

• Intelligence Inertia: Physical Isomorphism and Applications

  Jipeng Han · 7 April 2026

  Classical frameworks like Fisher Information approximate the cost of neural adaptation only in low-density regimes, failing to explain the explosive computational overhead incurred during deep structural reconfiguration. To address this, we introduce \textbf{Intelligence Inertia}, a property derived…

• The Price of Meaning: Why Every Semantic Memory System Forgets

  Sambartha Ray Barman, Andrey Starenky, Sofia Bodnar, Nikhil Narasimhan, Ashwin Gopinath · 31 March 2026

  Every major AI memory system in production today organises information by meaning. That organisation enables generalisation, analogy, and conceptual retrieval -- but it comes at a price. We prove that the same geometric structure enabling semantic generalisation makes interference, forgetting, and f…

• Intelligence Inertia: Physical Principles and Applications

  Jipeng Han · 25 March 2026

  While Landauer's principle establishes the fundamental thermodynamic floor for information erasure and Fisher Information provides a metric for local curvature in parameter space, these classical frameworks function effectively only as approximations within regimes of sparse rule-constraints. They f…

• Emotion-Gradient Metacognitive RSI (Part I): Theoretical Foundations and Single-Agent Architecture

  Rintaro Ando · 5 March 2026

  We present the Emotion-Gradient Metacognitive Recursive Self-Improvement (EG-MRSI) framework, a novel architecture that integrates introspective metacognition, emotion-based intrinsic motivation, and recursive self-modification into a unified theoretical system. The framework is explicitly capable o…

• Dynamic Manifold Hopfield Networks for Context-Dependent Associative Memory

  Chong Li, Taiping Zeng, Xiangyang Xue, Jianfeng Feng · 4 March 2026

  Neural population activity in cortical and hippocampal circuits can be flexibly reorganized by context, suggesting that cognition relies on dynamic manifolds rather than static representations. However, how such dynamic organization can be realized mechanistically within a unified dynamical system r…

• Dense associative memory for Gaussian distributions

  Chandan Tankala, Krishnakumar Balasubramanian · 3 February 2026

  Dense associative memories (DAMs) store and retrieve patterns via energy-function based fixed points, but existing models are limited to vector representations. We extend DAMs to Gaussian densities equipped with the 2-Wasserstein distance. Our framework defines a log-sum-exp energy over stored distr…

• Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework

  Hamid Reza Akbari, Mohammad Hossein Sameti, Amir M. Mansourian, Mohammad Hossein Rohban, Hossein Sameti · 2 February 2026

  The pursuit of Artificial General Intelligence (AGI) is a central goal in language model development, in which consciousness-like processing could serve as a key facilitator. While current language models are not conscious, they exhibit behaviors analogous to certain aspects of consciousness. This p…

• FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing

  Ran Elbaz, Guy Bar-Shalom, Yam Eitan, Fabrizio Frasca, Haggai Maron · 30 January 2026

  Permutation equivariant neural networks employing parameter-sharing schemes have emerged as powerful models for leveraging a wide range of data symmetries, significantly enhancing the generalization and computational efficiency of the resulting models. Recently, Kolmogorov-Arnold Networks (KANs) hav…