Image de couverture de livre

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Zhuo, Du, Guodong, Shi, Zesheng, Guo, Weiyang, Yao, Weijun, Zhou, Yuan, Zhang, Jiabo, Li, Jing
Format:	Preprint
Publié:	2026
Sujets:	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

Knowledge Fusion of Large Language Models Via Modular SkillPacks
par: Du, Guodong, et autres
Publié: (2025)

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
par: Guo, Weiyang, et autres
Publié: (2026)

Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement
par: Du, Jing, et autres
Publié: (2024)

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
par: Guo, Weiyang, et autres
Publié: (2025)

Safety Alignment via Constrained Knowledge Unlearning
par: Shi, Zesheng, et autres
Publié: (2025)

E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
par: Guo, Weiyang, et autres
Publié: (2026)

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
par: Zhou, Zhi, et autres
Publié: (2025)

Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment
par: Wang, Haozhong, et autres
Publié: (2026)

Efficient Skill Discovery via Regret-Aware Optimization
par: Zhang, He, et autres
Publié: (2025)

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
par: Li, Junlin, et autres
Publié: (2026)

Multi-objective Large Language Model Alignment with Hierarchical Experts
par: Li, Zhuo, et autres
Publié: (2025)

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
par: Ding, Yiwen, et autres
Publié: (2024)

Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs
par: Wang, Ruoyu, et autres
Publié: (2024)

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
par: Zhou, Zhi, et autres
Publié: (2025)

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
par: Qiu, Zeju, et autres
Publié: (2026)

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
par: Zhou, Tianyi, et autres
Publié: (2026)

Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion
par: Li, Minghan, et autres
Publié: (2026)

FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
par: Liu, Guangda, et autres
Publié: (2025)

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
par: Li, Donghao, et autres
Publié: (2026)

Agentic Web: Weaving the Next Web with AI Agents
par: Yang, Yingxuan, et autres
Publié: (2025)

ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning
par: Kagaya, Tomoyuki, et autres
Publié: (2025)

Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
par: Li, Xuan, et autres
Publié: (2026)

DOGMA: Weaving Structural Information into Data-centric Single-cell Transcriptomics Analysis
par: Zhang, Ru, et autres
Publié: (2026)

Reparameterized LLM Training via Orthogonal Equivalence Transformation
par: Qiu, Zeju, et autres
Publié: (2025)

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
par: Yang, Zhicheng, et autres
Publié: (2026)

Learning Versatile Skills with Curriculum Masking
par: Tang, Yao, et autres
Publié: (2024)

Ability Transfer and Recovery via Modularized Parameters Localization
par: Jin, Songyao, et autres
Publié: (2026)

Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
par: Zheng, Lingchao, et autres
Publié: (2026)

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
par: Chen, Guoxuan, et autres
Publié: (2024)

Amortized Reasoning Tree Search: Decoupling Proposal and Decision in Large Language Models
par: Hong, Zesheng, et autres
Publié: (2026)

Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution
par: Wu, Kaiqi, et autres
Publié: (2025)

Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
par: Chen, Zizhao, et autres
Publié: (2026)

EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness
par: Zhang, Yunxiao, et autres
Publié: (2025)

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach
par: Li, Zhiwei, et autres
Publié: (2024)

Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning
par: Liu, Ziwen, et autres
Publié: (2026)

DualWeaver: Synergistic Feature Weaving Surrogates for Multivariate Forecasting with Univariate Time Series Foundation Models
par: Li, Jinpeng, et autres
Publié: (2026)

Dynamic Model Merging Made Slim
par: Du, Guodong, et autres
Publié: (2026)

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
par: Wen, Yongyan, et autres
Publié: (2024)

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
par: Wilcoxson, Max, et autres
Publié: (2024)

Skill-R1: Agent Skill Evolution via Reinforcement Learning
par: Vishe, Yash, et autres
Publié: (2026)