analiza aiqbench
This research proposes Semantic Lenia, a novel framework that reimagines Large Language Model inference as a continuous dynamical system to prevent repetitive crystallization and foster abductive reasoning. By balancing semantic attraction with syntactic repulsion through homeostatic feedback loops, the study identifies critical regimes where models maintain generative stability while scaling capacity-dependent inertia across different model sizes.
Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models
arXiv:2608.11657v2 Announce Type: replace Abstract: We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference from a static optimization problem into a continuous, closed-loop dynamical system. By establishing a non-linear homeostatic feedback loop to dynamically balance semantic attraction and syntactic repulsion, we demonstrate the emergence of ``Homeostatic Solitons''-metastable semantic structures that actively resist repetitive crystallization. Our exhaustive parameter sweeps map a critical ``Habitable Ridge'' where applied steering forces balance the model's intrinsic syntactic inertia. This approach successfully maintains generative trajectories in a numerically sensitive critical regime, triggering profound abductive leaps without structural collapse, and reveals a capacity-dependent scaling trend in the syntactic inertia across different model sizes.
Abstract:We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference from a static optimization problem into a continuous, closed-loop dynamical system. By establishing a non-linear homeostatic feedback loop to dynamically balance semantic attraction and syntactic repulsion, we demonstrate the emergence of ``Homeostatic Solitons''-metastable semantic structures that actively resist repetitive crystallization. Our exhaustive parameter sweeps map a critical ``Habitable Ridge'' where applied steering forces balance the model's intrinsic syntactic inertia. This approach successfully maintains generative trajectories in a numerically sensitive critical regime, triggering profound abductive leaps without structural collapse, and reveals a capacity-dependent scaling trend in the syntactic inertia across different model sizes.
18 pages, 6 figures. Code, datasets, and interactive phase diagrams are available at this https URL
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Cellular Automata and Lattice Gases (nlin.CG)
arXiv:2608.11657 [cs.CL]
(or arXiv:2608.11657v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.11657 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 225 cuvinte
Subiecte conexe
Game Design Creativity evals
LessWrong · 12 oct. 2026
Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation
arXiv · 4 iun. 2026
Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation
arXiv · 3 iun. 2026
DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing
arXiv · 28 iul. 2026