Cover Image

SkillOrchestra: Learning to Route Agents via Skill Transfer

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jiayu, Ming, Yifei, Ke, Zixuan, Joty, Shafiq, Albarghouthi, Aws, Sala, Frederic
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
by: Wang, Jiayu, et al.
Published: (2025)

COSMOS: Predictable and Cost-Effective Adaptation of LLMs
by: Wang, Jiayu, et al.
Published: (2025)

LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild
by: Wang, Jiayu, et al.
Published: (2025)

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

MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision
by: Ke, Zixuan, et al.
Published: (2025)

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows
by: Ming, Yifei, et al.
Published: (2025)

NAACL2025 Tutorial: Adaptation of Large Language Models
by: Ke, Zixuan, et al.
Published: (2025)

Demystifying Domain-adaptive Post-training for Financial LLMs
by: Ke, Zixuan, et al.
Published: (2025)

MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
by: Ke, Zixuan, et al.
Published: (2026)

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
by: Ming, Yifei, et al.
Published: (2024)

Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings
by: Xu, Austin, et al.
Published: (2025)

Skill-R1: Agent Skill Evolution via Reinforcement Learning
by: Vishe, Yash, et al.
Published: (2026)

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
by: Shi, Zhenmei, et al.
Published: (2024)

OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation
by: Yang, Haochen, et al.
Published: (2026)

Variational Offline Multi-agent Skill Discovery
by: Chen, Jiayu, et al.
Published: (2024)

Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math
by: Pandit, Shrey, et al.
Published: (2025)

Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning
by: Wu, Lisheng, et al.
Published: (2024)

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills
by: Chen, Justin Chih-Yao, et al.
Published: (2025)

U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
by: Lee, Christine P, et al.
Published: (2026)

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

Pretrained Hybrids with MAD Skills
by: Roberts, Nicholas, et al.
Published: (2024)

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
by: Zhang, Haozhen, et al.
Published: (2026)

Hierarchical Orchestra of Policies
by: Cannon, Thomas P, et al.
Published: (2024)

Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning
by: Hao, Ce, et al.
Published: (2023)

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
by: He, Zhongyu, et al.
Published: (2026)

Learning to Transfer Human Hand Skills for Robot Manipulations
by: Park, Sungjae, et al.
Published: (2025)

Efficient Skill Discovery via Regret-Aware Optimization
by: Zhang, He, et al.
Published: (2025)

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
by: Che, Xinyu, et al.
Published: (2026)

SkillGen: Verified Inference-Time Agent Skill Synthesis
by: Ma, Yuchen, et al.
Published: (2026)

UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs
by: Shah, Devan, et al.
Published: (2026)

Memento-Skills: Let Agents Design Agents
by: Zhou, Huichi, et al.
Published: (2026)

Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
by: Nguyen, Xuan-Phi, et al.
Published: (2026)

DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
by: Liu, Xirui, et al.
Published: (2026)

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
by: He, Zelin, et al.
Published: (2026)

Choreographer: Learning and Adapting Skills in Imagination
by: Mazzaglia, Pietro, et al.
Published: (2022)

Learning Versatile Skills with Curriculum Masking
by: Tang, Yao, et al.
Published: (2024)

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
by: Wen, Yongyan, et al.
Published: (2024)

Robust Policy Learning via Offline Skill Diffusion
by: Kim, Woo Kyung, et al.
Published: (2024)

MRS: Multi-Resolution Skills for HRL Agents
by: Sharma, Shashank, et al.
Published: (2025)

NDST: Neural Driving Style Transfer for Human-Like Vision-Based Autonomous Driving
by: Kim, Donghyun, et al.
Published: (2024)