Saved in:
Bibliographic Details
Main Authors: Shao, Jie-Jing, Yin, Haiyan, Lyu, Yueming, Yu, Xingrui, Guo, Lan-Zhe, Tsang, Ivor, Kwok, James, Li, Yu-Feng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.01293
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.