发表机构
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机与人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Trace2Tower框架，通过转换感知特征轨迹诱导构建多级技能塔，在ALFWorld和WebShop基准测试中显著优于现有方法，提升了大语言模型智能体的任务掌握与经验复用能力。
AI 中文摘要
大语言模型智能体越来越依赖执行轨迹来掌握复杂的交互任务，但现有范式受限于浅层轨迹检索和扁平技能总结，根本上忽略了智能体行为的时间依赖性和结果条件拓扑结构。本文提出Trace2Tower，一种转换感知特征轨迹（EigenTrace）框架，可将原始轨迹提炼为稳健的技能层级。Trace2Tower将步骤级交互抽象为规范事件，构建受语义兼容性、转换动态性和结果证据约束的统一图；通过新型对比谱分解，分离出稳定、与成功对齐的行为模式，同时严格抑制易失败的捷径。这些模式自然构成包含动作模板、程序例程和总体任务策略的动态技能塔，经验证器引导的反馈持续优化。在ALFWorld上，Trace2Tower实现87.31%的成功率，仅需10.35步，无效动作仅0.26次；在WebShop上，其精确成功率达50.67%。在两个基准测试中，Trace2Tower在任务掌握和上下文高效经验复用方面均显著优于现有基线。
英文摘要
Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by shallow trajectory retrieval and flat skill summarization, fundamentally ignoring the temporal dependencies and outcome-conditioned topology of agent behavior. We introduce Trace2Tower, a transition-aware EigenTrace framework that distills raw trajectories into a robust skill hierarchy. Trace2Tower abstracts step-level interactions into canonical events, constructing a unified graph governed by semantic compatibility, transition dynamics, and outcome evidence. Through a novel contrastive spectral decomposition, it isolates stable, success-aligned behavioral modes while rigorously suppressing failure-prone shortcuts. These modes organically populate a dynamic skill tower of action templates, procedural routines, and overarching task strategies, continuously refined via verifier-guided feedback. On ALFWorld, Trace2Tower achieves 87.31% success requiring only 10.35 steps and 0.26 invalid actions; on WebShop, it reaches 50.67% exact success. Across both benchmarks, Trace2Tower significantly outperforms existing baselines in task mastery and context-efficient experience reuse.
Comments13 pages, 9 figures
