Image de couverture de livre

From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Binyan, Fang, Dong, Li, Haitao, Zhang, Kehuan
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Contextual Agentic Memory is a Memo, Not True Memory
par: Xu, Binyan, et autres
Publié: (2026)

When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
par: Li, Xiaoxiao
Publié: (2026)

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
par: Yang, Fan, et autres
Publié: (2026)

What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
par: Li, Xiaozhe, et autres
Publié: (2026)

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
par: Luo, Yinyi, et autres
Publié: (2026)

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

EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
par: Zhang, Aimin, et autres
Publié: (2026)

Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs
par: Unlu, Eren
Publié: (2026)

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

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

EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation
par: Long, Yunbo, et autres
Publié: (2026)

From Single Agent to Multi-Agent: Improving Traffic Signal Control
par: Tislenko, Maksim, et autres
Publié: (2024)

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

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

ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation
par: Yuan, Boqin, et autres
Publié: (2026)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
par: Wang, Su, et autres
Publié: (2026)

From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
par: Wu, Beining, et autres
Publié: (2026)

Odyssey: Empowering Minecraft Agents with Open-World Skills
par: Liu, Shunyu, et autres
Publié: (2024)

Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors
par: Feng, Lang, et autres
Publié: (2025)

SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
par: Yang, Min, et autres
Publié: (2026)

Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems
par: Xu, Andy, et autres
Publié: (2026)

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
par: Qiu, Jiahao, et autres
Publié: (2025)

More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
par: Song, Hongwen, et autres
Publié: (2026)

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
par: Yu, Zhengxu, et autres
Publié: (2026)

CUA-Skill: Develop Skills for Computer Using Agent
par: Chen, Tianyi, et autres
Publié: (2026)

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
par: Zhou, Yifan, et autres
Publié: (2026)

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
par: Huang, Zisu, et autres
Publié: (2026)

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
par: Gong, Jingzhi, et autres
Publié: (2026)

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
par: Li, Weizhen, et autres
Publié: (2025)

EvoSkill: Automated Skill Discovery for Multi-Agent Systems
par: Alzubi, Salaheddin, et autres
Publié: (2026)

Exploring Information Seeking Agent Consolidation
par: Yan, Guochen, et autres
Publié: (2026)

WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
par: Zhang, Zhisong, et autres
Publié: (2025)

SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
par: Zhang, Ziao, et autres
Publié: (2026)

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

SkillTester: Benchmarking Utility and Security of Agent Skills
par: Wang, Leye, et autres
Publié: (2026)

MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM
par: Lee, Woongkyu, et autres
Publié: (2025)

Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agent
par: Wang, Issue Yishu, et autres
Publié: (2025)

When Verification Hurts: Asymmetric Effects of Multi-Agent Feedback in Logic Proof Tutoring
par: Yasir, Tahreem, et autres
Publié: (2026)

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

CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making
par: Zou, Guowei, et autres
Publié: (2026)