Daily Paper Cast
Daily Paper Cast
Jingwen Liang, Gengyu Wang
Evolving Programmatic Skill Networks
25 minutes Posted Jan 9, 2026 at 3:17 am.
0:00
25:35
Download MP3
Show notes

🤗 Upvotes: 56 | cs.AI, cs.NE

Authors:

Haochen Shi, Xingdi Yuan, Bang Liu

Title:

Evolving Programmatic Skill Networks

Arxiv:

http://arxiv.org/abs/2601.03509v1

Abstract:

We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)REFLECT for structured fault localization over skill compositions, (2) progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3) canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.\footnote{We plan to open-source the code.