Image de couverture de livre

From Context to Skills: Can Language Models Learn from Context Skillfully?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Si, Shuzheng, Zhao, Haozhe, Lei, Yu, Wang, Qingyi, Chen, Dingwei, Wang, Zhitong, Wang, Zhenhailong, Luo, Kangyang, Wang, Zheng, Chen, Gang, Qi, Fanchao, Zhang, Minjia, Sun, Maosong
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

A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks
par: Si, Shuzheng, et autres
Publié: (2025)

FaithLens: Detecting and Explaining Faithfulness Hallucination
par: Si, Shuzheng, et autres
Publié: (2025)

GATEAU: Selecting Influential Samples for Long Context Alignment
par: Si, Shuzheng, et autres
Publié: (2024)

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
par: Bai, Yuzhuo, et autres
Publié: (2026)

Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
par: Si, Shuzheng, et autres
Publié: (2025)

RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
par: Lei, Yu, et autres
Publié: (2025)

Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
par: Si, Shuzheng, et autres
Publié: (2025)

From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition
par: Zhou, Yiqing, et autres
Publié: (2025)

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
par: Zhao, Haozhe, et autres
Publié: (2026)

Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
par: Zhao, Haozhe, et autres
Publié: (2024)

MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints
par: Luo, Kangyang, et autres
Publié: (2025)

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
par: Wang, Ran, et autres
Publié: (2025)

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
par: Gao, Cheng, et autres
Publié: (2026)

Can Language Models Compose Skills In-Context?
par: Liu, Zidong, et autres
Publié: (2025)

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion
par: Luo, Kangyang, et autres
Publié: (2025)

From History to State: Constant-Context Skill Learning for LLM Agents
par: Xie, Haoyang, et autres
Publié: (2026)

ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement
par: Luo, Kangyang, et autres
Publié: (2025)

Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
par: Chen, Jiaao, et autres
Publié: (2023)

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
par: Zhao, Haozhe, et autres
Publié: (2023)

SkillGen: Learning Domain Skills for In-Context Sequential Decision Making
par: Ding, Ruomeng, et autres
Publié: (2025)

SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
par: Meng, Xiangcheng, et autres
Publié: (2026)

Evolutionary Context Search for Automated Skill Acquisition
par: Sun, Qi, et autres
Publié: (2026)

MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
par: Zhao, Haozhe, et autres
Publié: (2025)

Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
par: An, Kaikai, et autres
Publié: (2024)

From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
par: Shen, Yingli, et autres
Publié: (2025)

DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection
par: Shen, Yingli, et autres
Publié: (2025)

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

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation
par: Zhao, Haozhe, et autres
Publié: (2024)

LooGLE: Can Long-Context Language Models Understand Long Contexts?
par: Li, Jiaqi, et autres
Publié: (2023)

In-context Autoencoder for Context Compression in a Large Language Model
par: Ge, Tao, et autres
Publié: (2023)

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

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
par: Wang, Zheng, et autres
Publié: (2024)

OSExpert: Computer-Use Agents Learning Professional Skills via Exploration
par: Liu, Jiateng, et autres
Publié: (2026)

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

From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models
par: Kuang, Ziyan, et autres
Publié: (2025)

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
par: Zhao, Haozhe, et autres
Publié: (2024)

State Anxiety Modulates Conflict Control Depending on Cognitive Control Context: Evidence From Behavioral and ERP Data
par: Zhitong Gong, 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)

CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models
par: Luo, Fuwen, et autres
Publié: (2024)

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