Metabolic Self-Organization: Emergence of Autonomous Agency in a Metabolically Constrained LLMs
Li, X.
Show 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.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Energy-ordered resource stratification as an agnostic signature of life 95%
- Latent Representations in Hippocampal Network Model Co-Evolve with Behavioral Exploration of Task Structure 95%
- Linear reinforcement learning: Flexible reuse of computation in planning, grid fields, and cognitive control 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.