Image de couverture de livre

From History to State: Constant-Context Skill Learning for LLM Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xie, Haoyang, Wang, Xinyuan, Wang, Yancheng, Zhao, Puda, Ju, Feng
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

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

From Context to Skills: Can Language Models Learn from Context Skillfully?
par: Si, Shuzheng, et autres
Publié: (2026)

Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
par: Zhang, Xi, et autres
Publié: (2026)

Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities
par: Xie, Haoyang, et autres
Publié: (2025)

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

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
par: Mi, Qirui, et autres
Publié: (2026)

Harnessing LLM Agents with Skill Programs
par: Liu, Hongjun, et autres
Publié: (2026)

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
par: Liu, Yuxuan, et autres
Publié: (2026)

TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents
par: Wang, Dawei, et autres
Publié: (2026)

MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills
par: Hou, Yingyong, et autres
Publié: (2026)

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
par: Wang, Jingxing, et autres
Publié: (2026)

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

SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment
par: Lin, Hongxiang, et autres
Publié: (2026)

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

Learning to Recommend Multi-Agent Subgraphs from Calling Trees
par: Song, Xinyuan, et autres
Publié: (2026)

SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
par: Miao, Yongliang, et autres
Publié: (2026)

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

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
par: Yu, Zhuoyun, et autres
Publié: (2026)

State Soup: In-Context Skill Learning, Retrieval and Mixing
par: Pióro, Maciej, et autres
Publié: (2024)

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
par: Liang, Qiliang, et autres
Publié: (2026)

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

SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
par: Hu, Wentao, et autres
Publié: (2026)

Federated In-Context LLM Agent Learning
par: Wu, Panlong, et autres
Publié: (2024)

Context Learning for Multi-Agent Discussion
par: Hua, Xingyuan, et autres
Publié: (2026)

Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention
par: Wang, Zhiming, 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)

Counterfactual Trace Auditing of LLM Agent Skills
par: Zhou, Xiaolin, et autres
Publié: (2026)

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

Reinforcement Learning for Self-Improving Agent with Skill Library
par: Wang, Jiongxiao, et autres
Publié: (2025)

AutoContext: Instance-Level Context Learning for LLM Agents
par: Cai, Kuntai, et autres
Publié: (2025)

CrimeMind: Simulating Urban Crime with Multi-Modal LLM Agents
par: Zeng, Qingbin, et autres
Publié: (2025)

The Scaling Laws of Skills in LLM Agent Systems
par: Chen, Charles, et autres
Publié: (2026)

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
par: Shi, Yaorui, et autres
Publié: (2026)

SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
par: Cho, Hongcheol, et autres
Publié: (2026)

SkillOrchestra: Learning to Route Agents via Skill Transfer
par: Wang, Jiayu, et autres
Publié: (2026)

A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing
par: Feng, Haoyang, et autres
Publié: (2025)

Learning CLI Agents with Structured Action Credit under Selective Observation
par: Su, Haoyang, et autres
Publié: (2026)

Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
par: Li, Xiaozhe, et autres
Publié: (2026)

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