Agent architectures

The varied neural network architectures used in the RL experiments to test whether the alignment phenomenon generalizes across architectures.

Neighborhood — ranked by edge-count

paper

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Agentconcept0.790
Any autonomous system including living and non-living forms that embodies a perception-action cycle and tries to navigate and persist in an environment
information architectureconcept0.784
Field Steenson worked in (1997 onwards); term denoting structural design of information systems; borrowed 'architecture' from computer design.
Artificial agentsconcept0.774
Synthetic agents (here RL-trained neural networks) whose causal emergence was previously largely unknown; the paper addresses this gap.
Agentic AI Systemsconcept0.774
Higher-level systems built on top of LLMs that produce and consume representations beyond next-token prediction; proposed as potential candidates for consciousness.
Agent-based modellingmethod0.769
Computational method used to simulate zombie ant behavior.
Agent-based computational modelmethod0.765
The computational approach used to simulate morphogenesis with cells as agents on a 2D grid; allows quantitative testing of stress-sharing hypothesis.
techno-architectureconcept0.763
Architecture as structure (computing)concept0.761
The definition of 'architecture' in computing as the structural design of systems, dating to 1960s mainframes, central to information architecture.