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

• URL: http://arxiv.org/abs/2606.05605v1
• Date: Thu, 04 Jun 2026 02:27:43 GMT
• Title: From Prediction to Self: Developmental Conditions for Agency in Minimal Neural Systems
• Abstract summary: We show how a system that merely predicts the world come to distinguish its own causal influence from everything else.<n>We propose agency gain (A = Err_world - Err_self), the predictive advantage of knowing one's own action, as a metric to track this process.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 40 controlled experiments arranged as a developmental sequence, adding components one at a time and tracking whether the system can distinguish self-caused from world-caused changes. The developmental path reveals four conditions that must be satisfied in strict order: (1) persistent state forming stable attractors, (2) a causal action loop linking output to input, (3) proprioceptive feedback that makes implicit causal knowledge explicit, and (4) asynchronous awakening - perceptual learning must consolidate before action learning begins. We propose agency gain (A = Err_world - Err_self), the predictive advantage of knowing one's own action, as a metric to track this process. The self-aware predictor consistently outperforms the self-blind predictor across periodic (sinusoidal) and chaotic (Lorenz) environments, and the metric survives ablation of all auxiliary components. Only forward-sampled action selection produces meaningful agency gain; two gradient-based alternatives degenerate. Equally significant are 12 falsified hypotheses mapping where development stalls: predictive coding alone does not produce self-represent

Related papers

• Orthogonal JEPA: Factorized Predictive States for Latent World Models [95.20158869896393]
  We introduce method, a latent world-modeling framework based on predictive factorization.<n>We show that method can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure.<n>Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability.
  arXiv  Detail & Related papers  (2026-08-20T13:59:57Z)
• Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle [0.0]
  Under the free energy principle, a predictive system does not observe reality directly.<n>It maintains a generative model of the world and experiences that model's best current hypothesis.<n>Can a synthetic environment be made consistent enough that a predictive system's own inference machinery adopts it as this default hypothesis?
  arXiv  Detail & Related papers  (2026-07-12T07:08:49Z)
• Causal Optimizer Interaction Calculus: Hidden Geometric Relaxation and Identifiable Interventions [0.0]
  We develop a causal intensity interaction calculus that separates pathwise realization, Mobius decomposition, and experimental identification.<n>Smooth hidden relaxation generates interactions through inverse structural stiffness.
  arXiv  Detail & Related papers  (2026-07-08T09:40:44Z)
• One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution [85.65263343588026]
  We propose SAGE, a Self-correcting, Autonomous, Grounded Experimenter.<n>Its core mechanism, Multi-Hypothesis Failure Attribution (MHFA), treats recovery as a structured causal diagnosis.<n>On a 12-topic, 5-domain benchmark, SAGE increases metrics-bearing outputs from 42% to 92% over a baseline reflection.
  arXiv  Detail & Related papers  (2026-06-30T10:54:16Z)
• Same World, Differently Given: History-Dependent Perceptual Reorganization in Artificial Agents [0.0]
  I present a minimal architecture in which a slow perspective latent $g$ feeds back into perception and is itself updated through perceptual processing.<n>This allows identical observations to be encoded differently depending on the agent's accumulated stance.<n>Only adaptive self-modulation yields the characteristic growth-then-stabilization dynamic, unlike rigid or always-open update regimes.
  arXiv  Detail & Related papers  (2026-04-06T12:39:22Z)
• Telogenesis: Goal Is All U Need [8.585574846949628]
  We propose a priority function that generates observation targets from three gaps: ignorance, surprise, and staleness.<n>We validate this in two systems: a minimal attention-allocation environment (2,000 runs) and a modular, partially observable world (500 runs.<n>A key finding is metric-dependent reversal: under global prediction error, coverage-based rotation wins; under change detection latency, priority-guided allocation wins, with advantage growing monotonically with dimensionality.
  arXiv  Detail & Related papers  (2026-03-10T10:28:45Z)
• OrthoFormer: Instrumental Variable Estimation in Transformer Hidden States via Neural Control Functions [0.0]
  Transformer architectures excel at sequential modeling yet remain fundamentally limited by correlational learning.<n>We propose OrthoFormer, a causally grounded architecture that embeds instrumental variable estimation directly into Transformer blocks via neural control functions.
  arXiv  Detail & Related papers  (2026-03-08T03:05:16Z)
• Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
  We propose to expose captured knowledge in the form of a directed acyclic causal graph. We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-09-30T20:59:42Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Neuro-Symbolic Entropy Regularization [78.16196949641079]
  In structured prediction, the goal is to jointly predict many output variables that together encode a structured object. One approach -- entropy regularization -- posits that decision boundaries should lie in low-probability regions. We propose a loss, neuro-symbolic entropy regularization, that encourages the model to confidently predict a valid object.
  arXiv  Detail & Related papers  (2022-01-25T06:23:10Z)
• Understanding Interlocking Dynamics of Cooperative Rationalization [90.6863969334526]
  Selective rationalization explains the prediction of complex neural networks by finding a small subset of the input that is sufficient to predict the neural model output. We reveal a major problem with such cooperative rationalization paradigm -- model interlocking. We propose a new rationalization framework, called A2R, which introduces a third component into the architecture, a predictor driven by soft attention as opposed to selection.
  arXiv  Detail & Related papers  (2021-10-26T17:39:18Z)

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.