Telogenesis: Goal Is All U Need

TL;DR

This paper introduces an endogenous attention mechanism based on epistemic gaps, enabling agents to generate adaptive priorities without external goals, validated through simulations showing improved environmental understanding and task performance.

Contribution

It proposes a novel priority function driven by epistemic gaps, demonstrating that internal cognitive states can produce effective attention allocation without external goals.

Findings

Epistemic gaps alone suffice for adaptive attention.

Priority-guided allocation outperforms coverage-based strategies in certain metrics.

System spontaneously recovers environmental volatility structure without supervision.

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.