Image de couverture de livre

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Che, Xinyu, Xiong, Junqi, Ge, Yunfei, Lei, Xinping, Li, Shihao, Yan, Hang, Li, Han, Zhang, Yuanxing, Bai, Zhiqi, Hao, Jinhua, Sun, Ming, Liu, Jiaheng
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Vibe AIGC: A New Paradigm for Content Generation via Agentic Orchestration
par: Liu, Jiaheng, et autres
Publié: (2026)

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

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

EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
par: Ju, Ruofei, et autres
Publié: (2026)

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

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

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

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
par: Zhang, Hanrong, et autres
Publié: (2026)

CODESKILL: Learning Self-Evolving Skills for Coding Agents
par: Li, Yanzhou, et autres
Publié: (2026)

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

SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
par: Liu, Xingyan, et autres
Publié: (2026)

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
par: Chen, Shiqi, et autres
Publié: (2026)

SAGER: Self-Evolving User Policy Skills for Recommendation Agent
par: Tao, Zhen, et autres
Publié: (2026)

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
par: Xu, Duling, et autres
Publié: (2026)

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
par: Liu, Yi, et autres
Publié: (2026)

From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?
par: Xu, Binyan, et autres
Publié: (2026)

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

ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
par: Zhu, Jie, et autres
Publié: (2026)

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

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
par: Xia, Peng, et autres
Publié: (2026)

ReVeal: Self-Evolving Code Agents via Reliable Self-Verification
par: Jin, Yiyang, et autres
Publié: (2025)

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
par: Li, Yubo, et autres
Publié: (2026)

Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
par: Zhou, Yifei, et autres
Publié: (2024)

Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
par: Tian, Yu, et autres
Publié: (2026)

AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
par: Wang, Pan, et autres
Publié: (2026)

Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering
par: Zhang, Xinyu, et autres
Publié: (2026)

Agent Skills Should Go Beyond Text: The Case for Visual Skills
par: Xu, Binxiao, et autres
Publié: (2026)

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
par: Ni, Jingwei, et autres
Publié: (2026)

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

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
par: Lin, Huawei, et autres
Publié: (2026)

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
par: Lei, Xinping, et autres
Publié: (2026)

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
par: Wu, Xiyang, et autres
Publié: (2026)

Auxiliary Metrics Help Decoding Skill Neurons in the Wild
par: Zhao, Yixiu, et autres
Publié: (2025)

SkillsInjector: Dynamic Skill Context Construction for LLM Agents
par: Li, Yanchao, et autres
Publié: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
par: Feng, Yunhao, et autres
Publié: (2026)

Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
par: Li, Xinze, et autres
Publié: (2026)

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
par: Liu, Yujian, et autres
Publié: (2026)

SkillGen: Verified Inference-Time Agent Skill Synthesis
par: Ma, Yuchen, et autres
Publié: (2026)

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

Evolving Programmatic Skill Networks
par: Shi, Haochen, et autres
Publié: (2026)