Imagen de Portada

The Scaling Laws of Skills in LLM Agent Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Charles, Yu, Qiming, Gu, Yuhang, Huang, Zhuoye, Li, Hanjing, Liu, Hongyu, Liu, Simin, Liu, Jinhao, Peng, Dengyun, Wang, Jiangyi, Yan, Zheng, Meng, Fanqing, Qin, Ethan, Che, Carl, Hu, Mengkang
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Do Coding Agents Understand Least-Privilege Authorization?
por: Yan, Zheng, et al.
Publicado: (2026)

Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models
por: Chen, Qiguang, et al.
Publicado: (2025)

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
por: Chen, Qiguang, et al.
Publicado: (2025)

Electronic Circuit Principles of Large Language Models
por: Chen, Qiguang, et al.
Publicado: (2025)

AutoPR: Let's Automate Your Academic Promotion!
por: Chen, Qiguang, et al.
Publicado: (2025)

DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective
por: Peng, Dengyun, et al.
Publicado: (2025)

AI4Research: A Survey of Artificial Intelligence for Scientific Research
por: Chen, Qiguang, et al.
Publicado: (2025)

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
por: Chen, Qiguang, et al.
Publicado: (2025)

Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks
por: Guan, Jiannan, et al.
Publicado: (2025)

Learning the Boundary of Solvability: Aligning LLMs to Detect Unsolvable Problems
por: Peng, Dengyun, et al.
Publicado: (2025)

The Universal Landscape of Human Reasoning
por: Chen, Qiguang, et al.
Publicado: (2025)

Measuring Interlayer Dependence of Large Degrees in Multilayer Inhomogeneous Random Graphs
por: Han, Zhuoye, et al.
Publicado: (2025)

Fixed‐Time Consensus Tracking of Second‐Order Multi‐Agent Systems by Sliding Mode Control
por: Yajuan Liu, et al.
Publicado: (2025)

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

Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
por: Cheng, Zihao, et al.
Publicado: (2026)

Gym-V: A Unified Vision Environment System for Agentic Vision Research
por: Meng, Fanqing, et al.
Publicado: (2026)

Multilayer Network Regression with Eigenvector Centrality and Community Structure
por: Han, Zhuoye, et al.
Publicado: (2023)

SkillRouter: Skill Routing for LLM Agents at Scale
por: Zheng, YanZhao, et al.
Publicado: (2026)

X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System
por: Wang, Peng, et al.
Publicado: (2025)

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

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
por: Jia, Xiaojun, et al.
Publicado: (2026)

AgentFL: Scaling LLM-based Fault Localization to Project-Level Context
por: Qin, Yihao, et al.
Publicado: (2024)

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

$λ_A$: A Typed Lambda Calculus for LLM Agent Composition
por: Liu, Qin
Publicado: (2026)

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
por: Pan, Shuai, et al.
Publicado: (2026)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
por: Chen, Zhihao, et al.
Publicado: (2026)

SkillsInjector: Dynamic Skill Context Construction for LLM Agents
por: Li, Yanchao, et al.
Publicado: (2026)

Counterfactual Trace Auditing of LLM Agent Skills
por: Zhou, Xiaolin, et al.
Publicado: (2026)

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
por: Wang, Jingxing, et al.
Publicado: (2026)

Scaling Laws for Agent Harnesses via Effective Feedback Compute
por: Zhang, Xuanliang, et al.
Publicado: (2026)

Small Fluorinated Aromatic Molecule‐Based Radiofrequency Identification Tags Enabled by Stepwise Tuning of Nuclear Shielding
por: Yuhang Jiang, et al.
Publicado: (2025)

Online Lifecycle Operating Costs Minimization Strategy for Fuel Cell Buses Considering Power Sources Degradation
por: Dongchen Qin, et al.
Publicado: (2024)

Scaling Laws for Educational AI Agents
por: Wu, Mengsong, et al.
Publicado: (2026)

SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
por: Cho, Hongcheol, et al.
Publicado: (2026)

SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation
por: Liu, Hao, et al.
Publicado: (2026)

Unveiling Supervisor‐Student Interactions: Patterns, Fluctuations, and Influencing Factors of Chinese Postgraduate EFL Learners’ Online Interaction With the Supervisor
por: Hongying Peng, et al.
Publicado: (2025)

Developmental dynamics in oral fluency and learner motivation: A dual‐focus approach
por: Hanjing Yu, et al.
Publicado: (2024)

Reinformer: Max-Return Sequence Modeling for Offline RL
por: Zhuang, Zifeng, et al.
Publicado: (2024)

CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
por: Pan, Ruwei, et al.
Publicado: (2025)

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
por: Trae Research Team, et al.
Publicado: (2025)