将轨迹提升到逻辑：基于神经符号学习的程序化技能诱导用于长视界代理任务
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
AI总结：
本文提出NSI框架，通过将交互轨迹提升为模块化逻辑 grounded 程序，使代理能从少量示例中归纳技能并适应新目标，优于现有方法。
摘要：
基于模型的代理在长视界规划中常因纯提示式推理的短暂性而受挫。现有技能归纳方法通过将经验转化为状态盲参数化脚本缓解此问题，但无法捕捉动态环境所需条件逻辑。本文提出神经符号技能归纳（NSI）框架，通过合成显式控制流和动态变量绑定，使代理能发现何时及为何行动。此范式实现了高效的泛化能力，使代理能从少量示例中归纳技能并灵活适应未见目标。在一系列代理任务中的实验表明，NSI在多个指标上均优于现有最先进基线，使代理能够自我进化为逻辑 grounded 技能的建筑师。
英文摘要：
Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind parameterized scripts, they fail to capture the conditional logic required for robust execution in dynamic environments. In this paper, we propose Neuro-Symbolic Skill Induction (NSI), a framework that lifts interaction traces into modular, \textit{logic-grounded} programs. By synthesizing explicit control flows and dynamic variable binding, NSI empowers agents to discover \textit{when} and \textit{why} to act. This paradigm enables the efficient generalization, allowing agents to induce skills from few-shot examples and flexibly adapt to unseen goals. Experiments on a series of agentic tasks demonstrate that NSI consistently outperforms state-of-the-art baselines, empowering agents to self-evolve into architects of logic-grounded skills.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
