Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents

• URL: http://arxiv.org/abs/2607.20708v1
• Date: Wed, 22 Jul 2026 20:25:29 GMT
• Title: Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents
• Abstract summary: I test how reward-free predictive organization relates to information-theoretic signatures in an active inference agent.<n>Results identify $g$ as the architectural locus of $_r$-relevant temporal organization in an active inference agent.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that $Φ_r$ grows with training and tracks reward improvement. For active inference, this raises the question of how reward-free predictive organization relates to such information-theoretic signatures. I test this within an active inference agent whose architecture separates a fast perception latent $z$ from a slow global latent $g$, where $g$ is driven by prediction error and structurally decoupled from policy gradients. In a reward-free environmental regime-switching protocol, $Φ_r$ concentrates in $g$; its aggregate magnitude is largely architectural and decreases with training. The substantive effect of learning becomes legible only at the atom-compositional level: decoupling flips sign from negative to positive and becomes regime-invariant under environmental change, while downward causation carries the regime-dependent adjustment. These results identify $g$ as the architectural locus of $Φ_r$-relevant temporal organization in an active inference agent, and argue against reading scalar $Φ_r$ as a direct index of learned integration.

Related papers

• Counterfactual Shapley Credit Assignment [49.39649767581182]
  Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents.<n>We introduce Counterfactual Shapley Credit Assignment, a novel framework that attributes credit and blame via the Counterfactual Shapley ($$-value)<n>We derive a consistent estimator that computes $$$-values, enabling a new class of policy methods, $$-PPO, combined with Prioritized Trajectory Replay (PTR)
  arXiv  Detail & Related papers  (2026-07-18T23:28:20Z)
• Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape [10.96851791770302]
  We study why closed-loop knowledge systems saturate and what external information can move them beyond their current attractors.<n>We introduce a three-level operational framework in which knowledge states $x_t$ evolve through transition kernels $K_$ indexed by a structural parameter $$.<n>We characterize escape through a metric condition on intervention-induced attractor displacement and a baseline-relative KL lower bound for increasing escape probability.
  arXiv  Detail & Related papers  (2026-07-15T15:06:15Z)
• Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization [56.150184676745205]
  Video anomaly understanding (VAU) relies on sparse, context-dependent cues.<n>We propose $Anomtext-$, a closed-loop framework that reconceptualizes video understanding as an active sequential decision-making process.<n>Inspired by human video-reviewing behavior, this framework unifies internal cognitive reasoning and strategic evidence acquisition into an interleaved policy.
  arXiv  Detail & Related papers  (2026-07-01T08:41:49Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• A Mathematical Framework for Temporal Modeling and Counterfactual Policy Simulation of Student Dropout [0.0]
  Dropout is operationalized as a time-to-event outcome at the enrollment level.<n>Weekly risk is modeled in discrete time via penalized, class-balanced logistic regression over person--period rows.<n>Under a late-event temporal holdout, the model attains row-level AUCs of 0.8350 (train) and 0.8405 (test)
  arXiv  Detail & Related papers  (2026-04-10T02:26:23Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Phase Transition for Budgeted Multi-Agent Synergy [41.486076708302456]
  Multi-agent systems can improve reliability, yet under a fixed inference budget they often help, saturate, or even collapse.<n>We develop a minimal and calibratable theory that predicts these regimes from three binding constraints of modern agent stacks.
  arXiv  Detail & Related papers  (2026-01-24T05:32:50Z)
• Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification [30.16664767564679]
  We show that shifts in LayerNorm parameters after fine-tuning are indicative of the transitions between source and target domains.<n>Our findings illuminate the underexplored dynamics of LayerNorm in transfer learning and provide practical strategies for LayerNorm fine-tuning.
  arXiv  Detail & Related papers  (2025-08-11T03:18:47Z)
• Extreme Memorization via Scale of Initialization [72.78162454173803]
  We construct an experimental setup in which changing the scale of initialization strongly impacts the implicit regularization induced by SGD. We find that the extent and manner in which generalization ability is affected depends on the activation and loss function used. In the case of the homogeneous ReLU activation, we show that this behavior can be attributed to the loss function.
  arXiv  Detail & Related papers  (2020-08-31T04:53:11Z)

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.