Image de couverture de livre

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Jingxing, Zhou, Chenyu, Fu, Zhihui, Wang, Jun, Liu, Weiwen, Zhang, Weinan, Lin, Jianghao
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
par: Pan, Shuai, et autres
Publié: (2026)

A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
par: Xi, Yunjia, et autres
Publié: (2025)

Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
par: Zhu, Jiachen, et autres
Publié: (2025)

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
par: Liang, Qiliang, et autres
Publié: (2026)

MMSkills: Towards Multimodal Skills for General Visual Agents
par: Zhang, Kangning, et autres
Publié: (2026)

The Scaling Laws of Skills in LLM Agent Systems
par: Chen, Charles, et autres
Publié: (2026)

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
par: Wang, Hao, et autres
Publié: (2026)

SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
par: Hu, Wentao, et autres
Publié: (2026)

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
par: Zeng, Kun, et autres
Publié: (2026)

SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval
par: Cui, Zicai, et autres
Publié: (2026)

Memento-Skills: Let Agents Design Agents
par: Zhou, Huichi, et autres
Publié: (2026)

Adaptive Milestone Reward for GUI Agents
par: Zheng, Congmin, et autres
Publié: (2026)

SkillOS: Learning Skill Curation for Self-Evolving Agents
par: Ouyang, Siru, et autres
Publié: (2026)

Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
par: Cheng, Zihao, et autres
Publié: (2026)

SkillOpt: Executive Strategy for Self-Evolving Agent Skills
par: Yang, Yifan, et autres
Publié: (2026)

Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
par: Xiong, Feng, et autres
Publié: (2026)

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

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
par: Zhang, Haozhen, et autres
Publié: (2026)

WebXSkill: Skill Learning for Autonomous Web Agents
par: Wang, Zhaoyang, et autres
Publié: (2026)

ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks
par: Song, Yuanyi, et autres
Publié: (2025)

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
par: Liu, Hongyi, et autres
Publié: (2026)

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
par: Zhang, Xing, et autres
Publié: (2026)

TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering
par: Han, Liying, et autres
Publié: (2026)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
par: Zheng, Congmin, et autres
Publié: (2025)

Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
par: Yang, Zonghan, et autres
Publié: (2025)

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

Superplatforms Have to Attack AI Agents
par: Lin, Jianghao, et autres
Publié: (2025)

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
par: Chai, Huacan, et autres
Publié: (2026)

Skill Path: Unveiling Language Skills from Circuit Graphs
par: Chen, Hang, et autres
Publié: (2024)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
par: Qu, Yubin, et autres
Publié: (2026)

GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
par: Moll, Johannes, et autres
Publié: (2026)

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

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
par: Zheng, Boyuan, et autres
Publié: (2025)

CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments
par: Fu, Lingyue, et autres
Publié: (2025)

SkillFlow: Scalable and Efficient Agent Skill Retrieval System
par: Li, Fangzhou, et autres
Publié: (2025)

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
par: Xu, Naen, et autres
Publié: (2026)

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
par: Che, Xinyu, et autres
Publié: (2026)

The AI Skills Shift: Mapping Skill Obsolescence, Emergence, and Transition Pathways in the LLM Era
par: Jadhav, Rudra, et autres
Publié: (2026)

Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning
par: Chen, Chishui, et autres
Publié: (2026)

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls
par: Zhang, Kangning, et autres
Publié: (2025)