Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks

2026-05-02

AI Summary

Existing foundation model–driven agents struggle to plan effectively in long-horizon tasks due to their reliance on instantaneous prompt-based reasoning, and current skill induction methods lack the capacity to model conditional logic in dynamic environments. This work proposes the Neural Symbolic Induction (NSI) framework, which for the first time leverages neural-symbolic methods to synthesize executable programs from interaction trajectories, explicitly encoding control flow and dynamic variable binding to enable interpretable reasoning about “when” and “why” to act. The approach supports few-shot skill induction and significantly outperforms state-of-the-art baselines across multiple agent tasks, demonstrating superior generalization and flexible adaptation to unseen goals.

Abstract

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.

Problem

• long-horizon planning
• skill induction
• conditional logic
• dynamic environments
• agentic tasks

Innovation

• Neuro-Symbolic Learning
• Skill Induction
• Logic-Grounded Programs
• Long-Horizon Planning
• Program Synthesis