Telogenesis: Goal Is All U Need

Zhuoran Deng; Yizhi Zhang; Ziyi Zhang; Wan Shen

cs.AIMar 10, 2026

Telogenesis: Goal Is All U Need

Authors: Zhuoran Deng, Yizhi Zhang, Ziyi Zhang, Wan Shen

Organizations: Independent Research

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.

Figures & tables

Strategy	Error ( $\pm$ SD)	vs. Pri. ( $p$ )	$d$	Attn. (sw.)
Random	$0.152\pm 0.032$	$<10^{-6}$	$-0.15$	0.500
Priority	$\mathbf{0.147\pm 0.030}$	—	—	0.534
Var-only	$0.148\pm 0.031$	$<0.001$	$-0.11$	0.509
Rotation	$0.132\pm 0.024$	$<10^{-8}$	$+0.54$	0.500
Error	$0.134\pm 0.025$	$<10^{-8}$	$+0.48$	0.533

Table 1: Minimal system (

N\!=\!6

, 2000 runs). Global prediction error, last 50%. Negative

d

= Priority is better.

Strategy	Error ( $\pm$ SD)	vs. Pri. ( $p$ )	$d$
Random	$0.267\pm 0.109$	$<10^{-6}$	$+0.31$
Rotation	$0.236\pm 0.108$	$0.961$	$+0.00$
Error	$0.381\pm 0.212$	$<10^{-8}$	$+0.89$
Priority	$\mathbf{0.236\pm 0.093}$	—	—

Table 2: Liminal (

N\!=\!16

, budget

\!=\!2

, 500 runs). Global prediction error.

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}

$N$	Rand.	Rot.	Pri.	Gap	$d$
8	4.01	3.90	3.25	0.65	$-0.27$
16	4.15	5.93	3.90	2.02	$-0.58$
24	4.10	6.79	4.10	2.70	$-0.72$
32	3.98	6.99	4.23	2.76	$-0.71$
48	4.11	7.66	4.03	3.63	$-0.95$

Table 3: Detection latency (ticks) by strategy and dimensionality. Budget

\!=\!1

, 500 runs. Priority vs. Rotation : all

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.

Var	Mod	Vol.	$\lambda_{i}$	Var	Mod	Vol.	$\lambda_{i}$
0	0	Hi	0.296	8	2	Lo	0.198
1	0	Hi	0.292	9	2	Lo	0.200
2	0	Hi	0.291	10	2	Lo	0.186
3	0	Hi	0.300	11	2	Lo	0.199
4	1	Hi	0.284	12	3	Lo	0.213
5	1	Hi	0.283	13	3	Lo	0.206

Table 4: Learned per-variable

\lambda_{i}

(50-run mean). Variables 0–7: high volatility (

p_{\text{trans}}\!=\!0.15

); variables 8–15: low volatility (

p_{\text{trans}}\!=\!0.02

). Paired

t

-test on per-run group means:

t(49)=22.5

p<10^{-6}

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}

Explore similar work

Attention when you need
Jan 13, 2025Grayson Matthew, Lokesh Boominathan, Yizhou Chen +2Temporal Attention
Neuroscience Institute Carnegie Mellon University, Pittsburgh, PA 15213 · Neuroscience Baylor College of Medicine, Houston, TX 77030 · Neuroscience Institute and Department of Machine Learning Carnegie Mellon University, Pittsburgh, PA 15213
Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent
Aug 4, 2026St John Grimbly, Nicolas Kuske, Evert A. Boonstra +7Adaptive Inference Active Inference
Dept. of Mathematics & Applied Mathematics, Univ. of Cape Town, South Africa · Neuroscience Institute, Univ. of Cape Town, South Africa · MIND Institute and CSAM, University of the Witwatersrand, South Africa +3
Emotional Preferences as Goal-Priority Regulation
Aug 27, 2026Shiqi Liu, Yihua Tan, Hu Fu +1Reinforcement Learning Preference Learning
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Luoyu Street, Wuhan, 430074, Hubei, China

Jan 13, 2025J/K move · Enter open · S save

Attention when you need

Grayson Matthew, Lokesh Boominathan, Yizhou Chen, Matthew McGinley+1

Neuroscience Institute Carnegie Mellon University, Pittsburgh, PA 15213 · Neuroscience Baylor College of Medicine, Houston, TX 77030 · Neuroscience Institute and Department of Machine Learning Carnegie Mellon University, Pittsburgh, PA 15213

Temporal Attention

Open paper AskPDF arXiv

Paying attention improves performance, but attention is metabolically costly, so how should a resource-efficient agent allocate it? We study optimal allocation strategies using a normative model of a signal detection task in which attention comes at a cost. The model reveals that optimal attention is temporally structured in one of two patterns depending on task conditions: when attention costs penalize intense focus, optimal attention ramps up as evidence for the signal accumulates, but with less prohibitive attention costs, optimal attention fluctuates rhythmically. In cases with rhythmic attention, allocation frequency increases with task parameters such as reward magnitude for successful detection, signal brevity, and signal frequency. We argue that rhythmic attention emerges naturally in an agent whose belief updates are dominated by a stable temporal prior and not by the likelihood of new sensory observations. Our results characterize the conditions under which rhythmic vs. ramping attention is optimal and offer a normative account of attentional fluctuations observed in sustained attention tasks.

Abstract

Explore similar work

Attention when you need

Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent

Emotional Preferences as Goal-Priority Regulation