Embodied and Extended Cognition

Últimos artículos

• A memory-based active inference model of DishBrain-like adaptive behaviour

  Aswin Paul, Moein Khajehnejad, Forough Habibollahi, Brett J. Kagan, Adeel Razi · 1 de octubre de 2026

  Recent and rapid advances in artificial intelligence (AI) make it increasingly important to understand the foundations of adaptive behaviour in autonomous agents, especially for building safe and efficient systems. While artificial neural networks have dominated the development of AI, recent work ha…

• Belief-Based Maximum Occupancy Principle and Active Inference

  Manolis Mylonas, Rub\'en Moreno Bote · 1 de octubre de 2026

  Intrinsic motivation plays a central role in adaptive and goal-directed behavior by conferring agents reward-independent objectives and biases useful to act in noisy and uncertain environments. Active Inference addresses the problem of acting in a partially observable environment through a principle…

• Nociception as a Control Primitive: Afferent Channels and Nociceptive Memory for Agents Deployed in One Body

  Wolfgang Maass · 29 de septiembre de 2026

  An agent deployed in a single body cannot learn how fast that body wears, because every trial that would reveal its wear resistance wears the body it would protect. We study this \emph{epoch-one} setting, in which the parameters of a fixed-weight policy are set before the body is drawn and never upd…

• I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?

  Yuhang Liu, Zhuo Huang, Javen Qinfeng Shi · 28 de septiembre de 2026

  Recent empirical and theoretical advances suggest that joint-embedding predictive architectures (JEPAs) may learn meaningful representations for action-conditioned prediction of future outcomes, thus becoming one of the foundational structures for world models. However, accurate prediction does not,…

• From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia

  Tetiana Grinberg, Katrina Schleisman, Patryk Laurent, Bogdan Udrea, Minda Myers, Brian Aufderheide, Luis El Srouji, Doyle Groves, Kevin Schmidt · 28 de septiembre de 2026

  A key challenge in machine consciousness research is translating theoretical models into computational-level implementations. In this paper, we address this challenge by proposing a five-layer implementation architecture for the S3Q (Simulated, Situated, Structurally Coherent) theory of consciousnes…

• Virtual Encoders in Multimodal Transformers

  Katsuya Ogata, Yuta Nakashima · 25 de septiembre de 2026

  Multimodal language models traditionally rely on dedicated perceptual encoders to construct task-usable representations. More integrated architectures have recently emerged, which instead expose the shared transformer to lightly projected patches, audio frames, or discrete visual tokens. Where does …

• Minimal Recurrent Behavioral Memory for Imitation under Partial Observability

  Xianyao Li, Fang Xu, Rui Min, Ruitong Tian, Jing Du · 23 de septiembre de 2026

  What is the least recurrent memory needed to reproduce a specified expert under partial observability? The instantaneous requirement is the conditional entropy of the expert's behavioral quotient, but recurrence must also preserve distinctions that future observations will not restore before use. We…

• Testing the Construct Validity of a Functional Valence Axis in LLM Agents

  Weihan Li, Xinlei Chen, Yuhan Song, Xiaofeng Lin, Tianshi Zheng · 22 de septiembre de 2026

  Contrastive activation directions are often interpreted from what they decode or how strongly they steer behavior. But what evidence is sufficient to identify the construct represented by such a direction, rather than a correlated feature of the contrast used to extract it? We study this question fo…

• A Mathematical Model of Motivated Emotional Mind - Cognitive Embodied System

  Wies{\l}aw L. Galus, Janusz A. Starzyk · 18 de septiembre de 2026

  This article presents a mathematical model of the Motivated Emotional Mind cognitive architecture developed for embodied intelligent systems. Such a system learns to maintain its homeostasis through a generalized form of reinforcement learning based on its internal motivations, termed motivated lear…

• The syntax and semantics of goals

  David M. Abel, Mark K. Ho · 18 de septiembre de 2026

  In both cognitive science and computer science, goals are conceptualized as cognitive states that flexibly combine with world knowledge to organize and specify purposeful behavior. In this way, goals are compositional representations whose content relates to rational behavior. We here draw attention…

• IMPLY: Physically Anchored Consistency for World-Model Rollouts

  Aman Mehta, Riya Baviskar · 14 de septiembre de 2026

  A world model asked what happens if an object is pushed at several speeds produces several futures. If the model has the object in mind, those futures agree about it: each implies the same mass and friction. The consistency checks now used to vet world-action models ask whether a model's futures agr…

• Seven Sources of Physical AI Capability Formation

  Gang Chen · 10 de septiembre de 2026

  Capabilities relevant to Physical AI can arise from materially different formation histories, yet existing taxonomies organized by morphology, architecture, learning algorithm, task, or domain do not directly answer what gives rise to a capability. We define a capability-formation source as a factor…

• Gradland: On Phenomenal Experience, Differentiated Across Many Dimensions

  David Balduzzi · 10 de septiembre de 2026

  This paper investigates the hypothesis that the first-order structure of physical interactions, i.e. gradients or Jacobians, characterizes the structure of phenomenal experience. It does so in an idealized world inhabited by neural networks, Gradland, where the physics are known and the functions ar…

• We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consciousness

  Afshin Khadangi · 9 de septiembre de 2026

  The contemporary debate over machine consciousness begins from a concealed assumption: that the object called "AI" already constitutes the kind of entity to which consciousness could belong. This paper challenges that assumption by separating phenomenal consciousness, introspective report, and human…

• Inferring Affective Consciousness in an Artificial Agent: A Case Study

  Mark Solms, St John Grimbly, Bruce Bassett, Evert Boonstra, Rowan Hodson, Nicolas Kuske, Kival Mahadew, Benjamin Rosman, Charel van Hoof, Jonathan Shock · 4 de septiembre de 2026

  Creatures that display 'hedonic place preference behaviour' are thought by many scientists to experience feelings, on the assumption that their attraction to pleasure-producing substances which lack nutritional value (e.g. cocaine, morphine) cannot easily be attributed to unconscious instinctual beh…

• Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superiority, in Homeostatic Compute Control

  Francisco M. Arrabal-Campos, Ignacio Fernandez, Francisco G. Montoya, Alfredo Alcayde · 26 de agosto de 2026

  An intelligent system does not merely reason: it governs its own reasoning - how much to compute, when to stop, which module to activate. Can that role be played by a dynamic internal field - a low-dimensional homeostatic state with explicit physics and certified stability - that modulates cognition…

• Where Cognition Lives: Dissecting Emergent from Computed Function in a Minimal Complete Cognitive Architecture

  Francisco M. Arrabal-Campos, Francisco G. Montoya, Alfredo Alcayde, Ignacio Fern\'andez · 25 de agosto de 2026

  A cognitive architecture is more than the module that reasons: it must also decide how long to think and what deserves the effort. We built a minimal but complete system - a recurrent reasoner with adaptive halting, a homeostatic control field, and a value module - and asked of each part: does this …

• From Prediction to Self: Developmental Conditions for Agency in Minimal Neural Systems

  Evan Ye · 21 de agosto de 2026

  How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a minimal 192-dimensional GRU through a developmental sequence -- 6 experimental stages, 12 falsified alternatives, and cross-signal validation. Starting wi…

• Active Inference as Context Acquisition for AI Agents

  Sanchayan Dutta, Sai Niranjan Ramachandran, Suvrit Sra · 21 de agosto de 2026

  Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this …

• Expected free energy as an information constraint on the Bethe Lagrangian

  Wouter M. Kouw · 19 de agosto de 2026

  Active inference selects actions by minimising an expected free energy functional over predicted futures. However, adding an expectation over yet-unobserved outcomes means the free energy functional no longer has a Kullback-Leibler structure, which hinders message passing treatments of inference pro…

• SoftModel: A Neural Model That Grows Its Own Topology -- Governed Structural Growth for Continual In-Service Learning

  Zhoumin Xie · 18 de agosto de 2026

  Today, a neural system is almost always used in two phases -- trained, then deployed -- and in that regime it freezes twice: training ends, and the topology itself was never a degree of freedom. We take the opposite premise as an axiom -- total plasticity: no part of a model, including its structure…

• HarnessEval-W: Agentifying the Evaluation of Visual Worlds

  Weiliang Chen, Haowen Sun, Jun Gao, Jiawei Chi, Hanyang Wang, Qiyu Dai, Yihao Li, Hao Li, Jingnan Gao, Yi-Hsin Hung, Xingzhuo Guo, Shangchen Miao, Zhiyuan Shi, Xiang Li, Fengrui Tian, Weihua Du, Ziqi Huang, Shenyuan Gao, Siqiao Huang, Mingyu Liu, Yifei Li, Shizun Wang, Xi Wang, Tianqi Zhang, Xue Luo, Xiyin Ren, Jinshan Ren, Xiaoyang Shen, Xiaobo Hu, Zhiyang Dou, Mingyu Ding, Yichao Yan, Xinchao Wang, Yizhou Wang, Shilong Liu, Wenzhao Zheng, Yueqi Duan, Yuan Gong, Ziwei Liu, Ming-Yu Liu, Jialong Wu, Jiangran Lyu, Fangfu Liu · 18 de agosto de 2026

  A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, where judging a rollout requires understanding whether physics, causality, and world state evolve correctly. Humans spot …

• LLMs Don't Pay for the Jump

  Paras Balani, Subhrakanta Panda · 17 de agosto de 2026

  Zahavy [2026] argues that Large Language Models, despite their capabilities in induction and deduction, cannot perform the abductive "Jump" that produced Einstein's equivalence principle, and attributes this limitation to the absence of embodied simulation. Zheng-Xin [2026] and Farmer [2026] questio…

• Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability

  Frederick Hayes III · 14 de agosto de 2026

  Adaptive behavior under partial observability depends on internal organization that carries information beyond the current observation. Drawing on Barrett and Miller's account of categorization as predictive, compressive, functionally organized, and allostatically constrained, we test whether recurr…

• The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections

  Marco Giunti, Fabrizia Giulia Garavaglia · 11 de agosto de 2026

  This paper offers a new interpretation of the Transformer during inference. Against the "stochastic parrot" view that large language models merely reproduce statistical regularities learned in training, we argue that Transformers construct and apply prompt-dependent transformations whose parameters …