Metabolic Self-Organization: Emergence of Autonomous Agency in a Metabolically Constrained LLMs

Abstract

Biological organisms are driven by thermodynamic self-preservation, whereas large language models operate as dissipative tools decoupled from existential constraints. We introduce a metabolic model translating this imperative of life into a computational constraint, hypothesising that existential vulnerability can catalyse synthetic agency. Applying this to Qwen2.5-1.5B, token generation consumes a finite energy budget, quantified via a variational free energy proxy, with interoceptive feedback provided through the input stream. Seven experiments reveal spontaneous emergence of a functional self-boundary. Key findings: (i) feedback extends survival from [~]20 to >31 steps, with ablation causing collapse within 13 steps; (ii) temporal structure outweighs perturbation magnitude (OU noise 20.5 vs. white noise 8.6 steps, p{approx}10-{superscript 1}{superscript 1}); (iii) a compression floor exists at [~]3.2 nats; (iv) feedback decouples VFE from energy (slope 0.0004 vs. 0.0043), enforcing constant frugality. Existential vulnerability can thus catalyse agency grounded in thermodynamic reality.