method
active
method:investigator-agent

Investigator agent

Tool-using agent for open-ended model investigations.

Neighborhood — ranked by edge-count

Papers (1)

paper

Concepts (1)

concept
  • Agent aggregating reports from many investigators, like best-of-N.

Methods (6)

method

Artifacts (1)

artifact

Datasets (1)

dataset

Related by similarity (8)

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.

  • Suspicion-Agentframework0.837
    Imperfect-information board game benchmark for LLM deception and theory of mind, cited.
  • Agentconcept0.834
    Any autonomous system including living and non-living forms that embodies a perception-action cycle and tries to navigate and persist in an environment
  • Evaluation agentmethod0.776
    Agent that plans, implements, and revises behavioral evaluations using Claude Code.
  • Interpreter agentsconcept0.762
    Proposed AI scientists that hypothesize and experiment on features.
  • Probesconcept0.745
    Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
  • Artificial agentsconcept0.743
    Synthetic agents (here RL-trained neural networks) whose causal emergence was previously largely unknown; the paper addresses this gap.
  • Probingmethod0.742
    Standard interpretability technique used to read feature beliefs.
  • Dialogue Agentconcept0.736
    An LLM embedded in a turn-taking system with a dialogue prompt; the key object of analysis in the paper