Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Telogenesis: Goal Is All U Need

Zhuoran Deng, Yizhi Zhang, Ziyi Zhang, Wan Shen

Abstract

Goal-conditioned systems assume goals are provided externally. We ask whether attentional priorities can emerge endogenously from an agent's internal cognitive state. We propose a priority function that generates observation targets from three epistemic gaps: ignorance (posterior variance), surprise (prediction error), and staleness (temporal decay of confidence in unobserved variables). We validate this in two systems: a minimal attention-allocation environment (2,000 runs) and a modular, partially observable world (500 runs). Ablation shows each component is necessary. 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 (d = -0.95 at N=48, p < 10^-6). Detection latency follows a power law in attention budget, with a steeper exponent for priority-guided allocation (0.55 vs. 0.40). When the decay rate is made learnable per variable, the system spontaneously recovers environmental volatility structure without supervision (t = 22.5, p < 10^-6). We demonstrate that epistemic gaps alone, without external reward, suffice to generate adaptive priorities that outperform fixed strategies and recover latent environmental structure.

Telogenesis: Goal Is All U Need

Abstract

Goal-conditioned systems assume goals are provided externally. We ask whether attentional priorities can emerge endogenously from an agent's internal cognitive state. We propose a priority function that generates observation targets from three epistemic gaps: ignorance (posterior variance), surprise (prediction error), and staleness (temporal decay of confidence in unobserved variables). We validate this in two systems: a minimal attention-allocation environment (2,000 runs) and a modular, partially observable world (500 runs). Ablation shows each component is necessary. 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 (d = -0.95 at N=48, p < 10^-6). Detection latency follows a power law in attention budget, with a steeper exponent for priority-guided allocation (0.55 vs. 0.40). When the decay rate is made learnable per variable, the system spontaneously recovers environmental volatility structure without supervision (t = 22.5, p < 10^-6). We demonstrate that epistemic gaps alone, without external reward, suffice to generate adaptive priorities that outperform fixed strategies and recover latent environmental structure.
Paper Structure (23 sections, 3 equations, 3 figures, 4 tables)

This paper contains 23 sections, 3 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. The Priority Function
  4. Experiment 1: Minimal System
  5. Design
  6. Component Ablation
  7. Results
  8. Experiment 2: Liminal
  9. Global Error: Replication of Minimal Results
  10. The Metric Reversal
  11. Detection Speed Scaling
  12. Power Law in Attention Budget
  13. Experiment 3: Emergent Structure Learning
  14. Motivation
  15. Design
  16. ...and 8 more sections

Figures (3)

  • Figure 1: Detection latency vs. number of variables ($N$), budget$\!=\!1$. Rotation degrades linearly with $N$; priority-guided allocation remains approximately constant. All comparisons $p < 10^{-6}$.
  • Figure 2: Detection latency vs. attention budget ($N\!=\!48$, log-log). Priority-guided allocation exhibits a steeper power law exponent (0.55 vs. 0.40), extracting greater marginal benefit from additional budget.
  • Figure 3: Learned $\lambda_i$ per variable (50-run mean). Red: high-volatility modules ($p_{\text{trans}}\!=\!0.15$); blue: low-volatility modules ($p_{\text{trans}}\!=\!0.02$). The system spontaneously differentiates volatility structure without supervision ($t = 22.5$, $p < 10^{-6}$).