mlsanityData to 7 Oct 2026

Evolving Programmatic Skill Networks

arXiv 2601.03509 ↗First posted 7 Jan 2026cs.AI cs.NEcited by 7

Not on the map. Why?

Abstract (arXiv)

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)~opreflect 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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 39 of its 62 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

39 of 62 references.

References · 39

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  9. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  10. 2016Progressive Neural Networkscited by 1,332
  11. 2014How transferable are features in deep neural networks?cited by 1,216
  12. 2015Automatic differentiation in machine learning: a surveycited by 846
27 more
  1. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  2. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  3. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  4. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
  5. 2016The Option-Critic Architecturecited by 433
  6. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  7. 2015Neural Module Networkscited by 375
  8. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  9. 2020Logic Tensor Networkscited by 197
  10. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 193
  11. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  12. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 149
  13. 2025Inducing Programmatic Skills for Agentic Taskscited by 103
  14. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 91
  15. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Taskscited by 83
  16. 2017Neural Task Programming: Learning to Generalize Across Hierarchical Taskscited by 75
  17. 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractionscited by 32
  18. 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policycited by 32
  19. 2024Odyssey: Empowering Minecraft Agents with Open-World Skillscited by 26
  20. 2018Composable Planning with Attributescited by 21
  21. 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoningcited by 20
  22. 2025WALT: Web Agents that Learn Toolscited by 15
  23. 2024ADAM: An Embodied Causal Agent in Open-World Environmentscited by 13
  24. 2024Language-guided Skill Learning with Temporal Variational Inferencecited by 11
  25. 2024Enhancing Agent Learning through World Dynamics Modelingcited by 9
  26. 2025One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Explorationcited by 9
  27. 2025Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problemscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  2. 2026Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Librariescited by 6
  3. 2026Mem-π: Adaptive Memory through Learning When and What to Generatecited by 3
  4. 2026Test-Time Learning with an Evolving Librarycited by 2
  5. 2026Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Securitycited by 0
  6. 2026LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillationcited by 0
  7. 2026MemCodex: Self-Programming Hierarchical Memory for Language Agentscited by 0