AgentBench

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

• Agentconcept0.808
  Any autonomous system including living and non-living forms that embodies a perception-action cycle and tries to navigate and persist in an environment
• Agent architecturesconcept0.751
  The varied neural network architectures used in the RL experiments to test whether the alignment phenomenon generalizes across architectures.
• AvalonBenchframework0.747
  Social deduction game benchmark (Avalon) for LLMs, cited.
• Biological agentsconcept0.747
  Natural living systems that have been shown to increase causal emergence after learning, motivating the cross-domain comparison.
• agent-environment boundaryconcept0.747
  The demarcation that would separate an agent from its environment, which the paper argues is unevidenceable.
• MoralBenchmethod0.744
  Benchmark for moral understanding in language models; cited as relevant existing evaluation tool
• Agent-based modellingmethod0.744
  Computational method used to simulate zombie ant behavior.
• Artificial agentsconcept0.743
  Synthetic agents (here RL-trained neural networks) whose causal emergence was previously largely unknown; the paper addresses this gap.