Trajectory Abstraction for the Science of Language Agent Behavior

arXiv:2610.09237v1 Announce Type: cross Abstract: 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. A concrete recursive procedure first measures role- and phase-indexed events, proposes temporally constrained relations, and tests their stability across conditions. It then constructs episode-level motif variables from selected relations and repeats the analysis on those variables. Explicit measurement functions connect every abstraction level to the original trajectories. Observations and randomized protocol experiments assess the resulting hypotheses, while comparisons between intervention realizations determine whether an abstraction should be retained, refined, or restricted. We derive a finite-depth bound for accepted reductions, identify protocol effects on fixed abstractions, and characterize realization disagreement and composition of abstraction error. A finite-sample test makes projected intervention consistency operational, and constructed examples illustrate motif construction and abstraction refinement. The formulation distinguishes this experimental approach from semantic taxonomies, qualitative theory induction, and behavior-model recovery. It specifies a proposed research procedure for discovering generalizable behavioral hypotheses, with literature-relative novelty assessed separately from model-relative surprise.

Related

• OTAP: Structure-Aware Optimal Transport for Evaluating Planning and Execution in Agent Trajectories
• Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
• A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks
• From Expert-Guided Proof Search to Automated Open-Problem Solving

Source: arXiv cs.CL | 2026-10-08