Evolving Programmatic Skill Networks
Haochen Shi · Xingdi Yuan · Bang Liu
Programmatic Skill Networks enable continual skill learning by evolving reusable executable programs for robust adaptation and generalization in open-ended environments.
摘要
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 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.