Trajectory Abstraction for the Science of Language Agent Behavior

Key points

• We formulate this research problem as learning and testing a hierarchy of trajectory abstractions.1
• A concrete recursive procedure first measures role- and phase-indexed events, proposes temporally constrained relations, and tests their stability across conditions.1
• We derive a finite-depth bound for accepted reductions, identify protocol effects on fixed abstractions, and characterize realization disagreement and composition of abstraction error.1
• The formulation distinguishes this experimental approach from semantic taxonomies, qualitative theory induction, and behavior-model recovery.1

Sources (1)

• [1]Trajectory Abstraction for the Science of Language Agent Behavior
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 11:58 PM

  Scientific studies of language agents need behavioral variables that support hypotheses across tasks and models.

  We formulate this research problem as learning and testing a hierarchy of trajectory abstractions.

Extractive summary: sentences quoted from the sources.