Evolving Programmatic Skill Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908750836662272 |
|---|---|
| author | Shi, Haochen Yuan, Xingdi Liu, Bang |
| author_facet | Shi, Haochen Yuan, Xingdi Liu, Bang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03509 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evolving Programmatic Skill Networks Shi, Haochen Yuan, Xingdi Liu, Bang Artificial Intelligence Neural and Evolutionary Computing I.2.6; I.2.2; I.2.8 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. |
| title | Evolving Programmatic Skill Networks |
| topic | Artificial Intelligence Neural and Evolutionary Computing I.2.6; I.2.2; I.2.8 |
| url | https://arxiv.org/abs/2601.03509 |