Image de couverture de livre

Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhu, Jiapeng, Yu, Jianxiang, Zhao, Yibo, Han, Chengcheng, Gu, Qi, Cai, Xunliang, Li, Xiang, Qian, Weining
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
par: Lu, Zhengxi, et autres
Publié: (2026)

RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning
par: Zhu, Jiapeng, et autres
Publié: (2024)

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
par: Yu, Jianxiang, et autres
Publié: (2026)

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
par: Shi, Yaorui, et autres
Publié: (2026)

HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
par: Wang, Jianing, et autres
Publié: (2026)

Class-Balanced and Reinforced Active Learning on Graphs
par: Yu, Chengcheng, et autres
Publié: (2024)

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
par: He, Zhongyu, et autres
Publié: (2026)

GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection
par: Wu, Zheng, et autres
Publié: (2026)

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
par: He, Zelin, et autres
Publié: (2026)

An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement
par: Shi, Haojie, et autres
Publié: (2024)

Self-Distilled Agentic Reinforcement Learning
par: Lu, Zhengxi, et autres
Publié: (2026)

GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence
par: Zhao, Yibo, et autres
Publié: (2026)

$V_{0.5}$: Generalist Value Model as a Prior for Sparse RL Rollouts
par: Zhang, Yi-Kai, et autres
Publié: (2026)

EffiSkill: Agent Skill Based Automated Code Efficiency Optimization
par: Wang, Zimu, et autres
Publié: (2026)

Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning
par: Shen, Junhao, et autres
Publié: (2026)

Agentic Skill Discovery
par: Zhao, Xufeng, et autres
Publié: (2024)

APEX: Academic Poster Editing Agentic Expert
par: Shi, Chengxin, et autres
Publié: (2026)

Relation-Aware Graph Foundation Model
par: Yu, Jianxiang, et autres
Publié: (2025)

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
par: Ma, Ziyu, et autres
Publié: (2026)

Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code Selection
par: Zeng, Long, et autres
Publié: (2025)

SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
par: Zhang, Mingda, et autres
Publié: (2026)

Skill-LLM: Repurposing General-Purpose LLMs for Skill Extraction
par: Herandi, Amirhossein, et autres
Publié: (2024)

Skill Reuse as Compression in Agentic RL
par: Xu, Zhikun, et autres
Publié: (2026)

Inducing Programmatic Skills for Agentic Tasks
par: Wang, Zora Zhiruo, et autres
Publié: (2025)

An Agentic AI Framework for Training General Practitioner Student Skills
par: De Marez, Victor, et autres
Publié: (2025)

Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models
par: Wang, Xin, et autres
Publié: (2026)

SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs
par: Li, Xiaoyuan, et autres
Publié: (2026)

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents
par: Xiao, Wenjie, et autres
Publié: (2026)

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
par: Yu, Zhuoyun, et autres
Publié: (2026)

SkillEvolver: Skill Learning as a Meta-Skill
par: Zhang, Genrui, et autres
Publié: (2026)

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
par: Xia, Peng, et autres
Publié: (2026)

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
par: Tasse, Geraud Nangue, et autres
Publié: (2022)

Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning
par: Hao, Ce, et autres
Publié: (2023)

Harnessing AtomisticSkills for Agentic Atomistic Research
par: Deng, Bowen, et autres
Publié: (2026)

AQETuner: Reliable Query-level Configuration Tuning for Analytical Query Engines
par: Chen, Lixiang, et autres
Publié: (2025)

MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction
par: Li, Yixuan, et autres
Publié: (2026)

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
par: Jiang, Pengcheng, et autres
Publié: (2025)

SkillX: Automatically Constructing Skill Knowledge Bases for Agents
par: Wang, Chenxi, et autres
Publié: (2026)

Skill-R1: Agent Skill Evolution via Reinforcement Learning
par: Vishe, Yash, et autres
Publié: (2026)

LEGO: An LLM Skill-Based Front-End Design Generation Platform
par: Lou, Jincheng, et autres
Publié: (2026)