arXiv：cs.CL· Tianqiang Yan·· 3 小时前AI 评分23
语言智能体行为科学中的轨迹抽象方法
Trajectory Abstraction for the Science of Language Agent Behavior
AI 导读
研究提出将语言智能体行为研究形式化为轨迹抽象层级的学习与测试，通过测量角色与阶段索引事件、提出时序约束关系并检验其跨条件稳定性，再从选定关系构建情节级 motif 变量并递归分析。该框架给出接受归约的有限深度界，刻画协议效应、实现分歧与抽象误差的复合，并用有限样本检验使投影干预一致性可操作。
正文
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.
| Comments: | (Work in Progress) 13 pages, 2 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.09237 [cs.AI] |
| (or arXiv:2610.09237v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09237 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tianqiang Yan [view email]
[v1]
Tue, 6 Oct 2026 23:58:44 UTC (39 KB)
来源：arXiv：cs.CL · arxiv.org