paper-with-me

Papers

Evolving Programmatic Skill Networks

2026-01-07 · Haochen Shi, Xingdi Yuan, Bang Liu 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.

📄 PDF Abstract BibTeX arXiv:2601.03509

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Inducing Programmatic Skills for Agentic Tasks

2025-04-09 · Zora Zhiruo Wang, Apurva Gandhi, Graham Neubig, Daniel Fried

To succeed in common digital tasks such as web navigation, agents must carry out a variety of specialized tasks such as searching for products or planning a travel route. To tackle these tasks, agents can bootstrap thems…

InnateCoder: Learning Programmatic Options with Foundation Models

2025-05-18 · Rubens O. Moraes, Quazi Asif Sadmine, Hendrik Baier, Levi H. S. Lelis

Outside of transfer learning settings, reinforcement learning agents start their learning process from a clean slate. As a result, such agents have to go through a slow process to learn even the most obvious skills requi…

Transfer Learning

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

2026-05-27 · Xujun Li, Kehan Zheng, Mingyuan Zhao, Yize Geng 외 arxiv

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter u…

REFLEX: Reflective Evolution from LLM Experience

2026-06-15 · Pan Wang arxiv

Large multimodal language models (LLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic policies. However, existing frameworks rely on a monolithic model call to simultane…

Code Generation

Programmatic Reinforcement Learning without Oracles

2021-09-29 · ICLR 2022 4 · Wenjie Qiu, He Zhu

Deep reinforcement learning (RL) has led to encouraging successes in many challenging control tasks. However, a deep RL model lacks interpretability due to the difficulty of identifying how the model's control logic rela…

Bilevel OptimizationDeep Reinforcement LearningPolicy Gradient Methodsreinforcement-learning+2