Vector-based navigation using grid-like representations in artificial agents (Banino et al., 2018)

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

• Emergence of grid-like representations by training recurrent neural networks to perform spatial localization (Cueva & Wei, 2018)concept0.808
  RNN model recapitulating grid cells; related work category 4.
• ATLAS: Agentic or Latent Visual Reasoningframework0.768
  Core framework proposing discrete functional tokens as a unified solution for visual reasoning in VLMs, bridging agentic and latent approaches.
• Steering vectors capture latent dimensions of reflective behavior more faithfully than surface-level embedding similarity.claim0.764
  Supported by the instruction discovery experiments comparing steering vs. embedding baselines.
• Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.763
  Central hypothesis tested via manifold steering experiments across language models and video world models.
• Steering vectors discover effective triggers such as 'However' and 'Otherwise', consistent with prior reported reflection datasetsfinding0.752
  Validates that steering vectors capture reflection semantics by finding tokens reported in related work.
• Neural Representations of Location Composed of Spatially Periodic Bands (Krupic et al., 2012)concept0.751
  Discovery of band cells; TEM-t also recapitulates these representations.
• Steering vectors enable systematic discovery of reflection-inducing instructions beyond trial-and-error prompt design.claim0.750
  Core applied contribution claim, supported by top-k accuracy comparisons.
• Steering vector-based instruction discovery outperforms input embedding similarity baseline for reflection-inducing instruction selectionfinding0.750
  Demonstrates that surface-level embedding similarity fails to capture reflective semantics.