Local 2- and 3-cycles enhance RNN computational capacity for Boolean functions, predicted by structural statistics, while adding interneurons boosts large networks.
Computational life: How well-formed, self-replicating programs emerge from simple interaction.arXiv preprint arXiv:2406.19108, 2024
4 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
4
Pith papers citing it
1
external citations · external index
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Agentic LLM collectives are proposed as natural-language-interpretable computational substrates for ALife research.
Simple mutation random walks locate self-replicators at least as easily as paired interactions, and ancestry depth/width caps block takeover but not initial emergence.
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.
citing papers explorer
-
Identifying structural design principles shaping the computational abilities of recurrent neural networks
Local 2- and 3-cycles enhance RNN computational capacity for Boolean functions, predicted by structural statistics, while adding interneurons boosts large networks.
-
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
Agentic LLM collectives are proposed as natural-language-interpretable computational substrates for ALife research.
-
BFF: Simple explanations for complex phenomena
Simple mutation random walks locate self-replicators at least as easily as paired interactions, and ancestry depth/width caps block takeover but not initial emergence.
-
Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.