Imagen de Portada

HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Jianing, Guo, Linsen, Chen, Zhengyu, Guo, Qi, Zang, Hongyu, Shi, Wenjie, Ma, Haoxiang, Xi, Xiangyu, Li, Xiaoyu, Wang, Wei, Cai, Xunliang
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
por: Zhu, Jiapeng, et al.
Publicado: (2026)

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
por: Wang, Jianing, et al.
Publicado: (2026)

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
por: Shi, Yaorui, et al.
Publicado: (2026)

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
por: Lu, Zhengxi, et al.
Publicado: (2026)

Harnessing AtomisticSkills for Agentic Atomistic Research
por: Deng, Bowen, et al.
Publicado: (2026)

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
por: Ma, Ziyu, et al.
Publicado: (2026)

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
por: Lu, Yi, et al.
Publicado: (2025)

Autoformalizer with Tool Feedback
por: Guo, Qi, et al.
Publicado: (2025)

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning
por: Wang, Jianing, et al.
Publicado: (2025)

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
por: Kong, Deyang, et al.
Publicado: (2025)

OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration
por: Guo, Qi, et al.
Publicado: (2026)

Possible bound states of Heavy Baryonium and Heavy Dibaryon systems
por: Qi, Jing-Juan, et al.
Publicado: (2024)

SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs
por: Li, Xiaoyuan, et al.
Publicado: (2026)

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
por: He, Zelin, et al.
Publicado: (2026)

Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions
por: Guo, Shuang, et al.
Publicado: (2025)

HALO:Closing Sim-to-Real Gap for Heavy-loaded Humanoid Agile Motion Skills via Differentiable Simulation
por: Wang, Xingyi, et al.
Publicado: (2026)

Skill Reuse as Compression in Agentic RL
por: Xu, Zhikun, et al.
Publicado: (2026)

Inducing Programmatic Skills for Agentic Tasks
por: Wang, Zora Zhiruo, et al.
Publicado: (2025)

Agentic Skill Discovery
por: Zhao, Xufeng, et al.
Publicado: (2024)

Affordance Agent Harness: Verification-Gated Skill Orchestration
por: Huang, Haojian, et al.
Publicado: (2026)

Factorization Formula Connecting the Shape Functions of Heavy Meson in QCD and Heavy Quark Effective Theory
por: Wang, Wei, et al.
Publicado: (2025)

Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization
por: Chen, Zhengyu, et al.
Publicado: (2025)

SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity
por: Xi, Xiangyu, et al.
Publicado: (2025)

To Retrieve or To Think? An Agentic Approach for Context Evolution
por: Chen, Rubing, et al.
Publicado: (2026)

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
por: Zhou, Junkai, et al.
Publicado: (2023)

Energy Loss of a Heavy Quark in a Collisional Quark-Gluon Plasma
por: Cai, Mingda, et al.
Publicado: (2025)

Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
por: Li, Xinze, et al.
Publicado: (2026)

Commonalities in Critical Thinking Skills Instruction and Library Skills Instruction.
por: Brown, Anita Fay
Publicado: (1993)

SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
por: Jiang, Yanna, et al.
Publicado: (2026)

Thinking Skills and Creativity Journal
Publicado: (2025)

Using Books for Thinking Skills.
Publicado: (1994)

Thinking (Higher Order) Skills.
por: Callison, Daniel
Publicado: (2002)

Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer
por: Zhang, Jing-Zong, et al.
Publicado: (2025)

Harnessing LLM Agents with Skill Programs
por: Liu, Hongjun, et al.
Publicado: (2026)

Linear Depth QFT over IBM Heavy-hex Architecture
por: Gao, Xiangyu, et al.
Publicado: (2024)

Interaction Effects of Lead and Cadmium Concentrations on Heavy Metal Accumulation and Transport in Rice
por: Lang Yang, et al.
Publicado: (2026)

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
por: Liu, Yuxuan, et al.
Publicado: (2026)

PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction
por: Yu, Simon, et al.
Publicado: (2025)

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
por: Zhao, Guangxiang, et al.
Publicado: (2026)

SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
por: Zhang, Mingda, et al.
Publicado: (2026)