Copertina

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Jianxiang, Zhu, Jiapeng, Lin, Bochen, Cui, Qier, Ding, Zichen, Li, Xiang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SEAGraph: Unveiling the Whole Story of Paper Review Comments
di: Yu, Jianxiang, et al.
Pubblicazione: (2024)

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

GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence
di: Zhao, Yibo, et al.
Pubblicazione: (2026)

One Size Does Not Fit All: A Distribution-Aware Sparsification for More Precise Model Merging
di: Luo, Yingfeng, et al.
Pubblicazione: (2025)

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

One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instruction
di: Liu, Ben, et al.
Pubblicazione: (2025)

Theorem Provers: One Size Fits All?
di: Oates, Harrison, et al.
Pubblicazione: (2025)

AlignEvoSkill: Towards Knowledge-Aware and Task-Aligned Agent Skill Evolution
di: Wang, Dingzirui, et al.
Pubblicazione: (2025)

Beyond One-Size-Fits-All: Personalized Harmful Content Detection with In-Context Learning
di: Zhang, Rufan, et al.
Pubblicazione: (2025)

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
di: Yu, Zhuoyun, et al.
Pubblicazione: (2026)

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
di: Chen, Shiqi, et al.
Pubblicazione: (2026)

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

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

Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
di: Hong, Hanhua, et al.
Pubblicazione: (2025)

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
di: Zhang, Xing, et al.
Pubblicazione: (2026)

The Scaling Laws of Skills in LLM Agent Systems
di: Chen, Charles, et al.
Pubblicazione: (2026)

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

"One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors
di: Lucy, Li, et al.
Pubblicazione: (2023)

No One Size Fits All: QueryBandits for Hallucination Mitigation
di: Cho, Nicole, et al.
Pubblicazione: (2026)

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
di: Zeng, Kun, et al.
Pubblicazione: (2026)

Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

Skill-LLM: Repurposing General-Purpose LLMs for Skill Extraction
di: Herandi, Amirhossein, et al.
Pubblicazione: (2024)

GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
di: Moll, Johannes, et al.
Pubblicazione: (2026)

SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
di: Hu, Wentao, et al.
Pubblicazione: (2026)

Beyond One-Size-Fits-All Summarization: Customizing Summaries for Diverse Users
di: Duran, Mehmet Samet, et al.
Pubblicazione: (2025)

Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
di: Wei, Kai, et al.
Pubblicazione: (2026)

One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache
di: Lu, Liming, et al.
Pubblicazione: (2026)

Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
di: Li, Hao, et al.
Pubblicazione: (2026)

One Size Fits None: Heuristic Collapse in LLM Investment Advice
di: Ross, Jillian, et al.
Pubblicazione: (2026)

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
di: Wang, Hao, et al.
Pubblicazione: (2026)

Beyond One-Size-Fits-All: Multi-Domain, Multi-Task Framework for Embedding Model Selection
di: Khetan, Vivek
Pubblicazione: (2024)

SkillOS: Learning Skill Curation for Self-Evolving Agents
di: Ouyang, Siru, et al.
Pubblicazione: (2026)

GraSP: Graph-Structured Skill Compositions for LLM Agents
di: Xia, Tianle, et al.
Pubblicazione: (2026)

SkillOpt: Executive Strategy for Self-Evolving Agent Skills
di: Yang, Yifan, et al.
Pubblicazione: (2026)

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
di: Liang, Qiliang, et al.
Pubblicazione: (2026)

EffiSkill: Agent Skill Based Automated Code Efficiency Optimization
di: Wang, Zimu, et al.
Pubblicazione: (2026)

SkillFlow: Scalable and Efficient Agent Skill Retrieval System
di: Li, Fangzhou, et al.
Pubblicazione: (2025)

One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction
di: Lu, Yuxing, et al.
Pubblicazione: (2026)

SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
di: Meng, Xiangcheng, et al.
Pubblicazione: (2026)

SkillX: Automatically Constructing Skill Knowledge Bases for Agents
di: Wang, Chenxi, et al.
Pubblicazione: (2026)