Evolving Programmatic Skill Networks
Abstract
Programmatic Skill Network enables continual skill acquisition through executable symbolic programs that evolve via reflection, progressive optimization, and structural refactoring mechanisms.
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.
Community
We study continual skill acquisition in openended 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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback (2025)
- MemEvolve: Meta-Evolution of Agent Memory Systems (2025)
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory (2026)
- Bridging Symbolic Control and Neural Reasoning in LLM Agents: The Structured Cognitive Loop (2025)
- From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory (2025)
- SkillWrapper: Generative Predicate Invention for Skill Abstraction (2025)
- EvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
arXiv explained breakdown of this paper 👉 https://arxivexplained.com/papers/evolving-programmatic-skill-networks
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper