# Same World, Differently Given: History-Dependent Perceptual Reorganization in Artificial Agents

arXiv: https://arxiv.org/abs/2604.04637 · HTML: https://mlsanity.com/paper/2604.04637/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 4 of 4)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Meta-Learning through Hebbian Plasticity in Random Networks](https://mlsanity.com/paper/2007.02686/) (2020)
- [Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity](https://mlsanity.com/paper/2002.10585/) (2020)
- [Minimal Computational Preconditions for Subjective Perspective in Artificial Agents](https://mlsanity.com/paper/2602.02902/) (2026)

## Built on by (most cited first, 2 of 2)

- [Body-Grounded Perspective Formation and Conative Attunement in Artificial Agents](https://mlsanity.com/paper/2605.16728/) (2026)
- [Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents](https://mlsanity.com/paper/2607.20708/) (2026)

## Abstract (arXiv)

What kind of internal organization would allow an artificial agent not only to adapt its behavior, but to sustain a history-sensitive perspective on its world? I present a minimal architecture in which a slow perspective latent g feeds back into perception and is itself updated through perceptual processing. This allows identical observations to be encoded differently depending on the agent's accumulated stance. The model is evaluated in a minimal gridworld with a fixed spatial scaffold and sensory perturbations. Across analyses, three results emerge. First, the perspective latent reorganizes perceptual encoding: identical observations are represented differently depending on prior experience, and this reorganization of salience gating replicates across runs, with five of 16 gating dimensions changing direction consistently across 30 independent runs after correction for multiple comparisons. Second, only adaptive self-modulation yields the characteristic growth-then-stabilization dynamic of the perspective latent, unlike rigid or always-open update regimes. Third, perturbation history is followed by reduced adaptive plasticity after nominal conditions are restored, showing a directionally consistent trend across seeds. Gross behavior remains stable throughout the analysis, suggesting that the dominant reorganization is perceptual rather than behavioral. Together, these findings identify a minimal mechanism for history-dependent perspectival organization in artificial agents.