Imagen de Portada

MetaToolAgent: Towards Generalizable Tool Usage in LLMs through Meta-Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fang, Zheng, Mayer, Wolfgang, Zhang, Zeyu, Wang, Jian, Zhang, Hong-Yu, Li, Wanli, Feng, Zaiwen
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Practical Tool Usage for Continually Learning LLMs
por: Huang, Jerry, et al.
Publicado: (2024)

ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents
por: Wang, Xiaoce, et al.
Publicado: (2026)

MetaTool: Facilitating Large Language Models to Master Tools with Meta-task Augmentation
por: Wang, Xiaohan, et al.
Publicado: (2024)

Generalizable Heuristic Generation Through LLMs with Meta-Optimization
por: Shi, Yiding, et al.
Publicado: (2025)

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
por: Xia, Peng, et al.
Publicado: (2026)

Good Tools are Half the Work: Tool Usage in Deep Learning Projects
por: Panourgia, Evangelia, et al.
Publicado: (2023)

LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
por: Wang, Boshi, et al.
Publicado: (2024)

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning
por: Zhang, Baoquan, et al.
Publicado: (2023)

Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models
por: Kumar, Sachin
Publicado: (2026)

Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement Learning
por: Zhou, Shicheng, et al.
Publicado: (2024)

CACTUS: Chemistry Agent Connecting Tool-Usage to Science
por: McNaughton, Andrew D., et al.
Publicado: (2024)

Towards an Adaptable and Generalizable Optimization Engine in Decision and Control: A Meta Reinforcement Learning Approach
por: Yang, Sungwook, et al.
Publicado: (2024)

Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation
por: Lyu, Bohan, et al.
Publicado: (2024)

Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
por: Li, Lanqing, et al.
Publicado: (2024)

MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure
por: Zhang, Zhicheng, et al.
Publicado: (2024)

Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks
por: Zhang, Lei, et al.
Publicado: (2024)

ToolExpander: Extending the Frontiers of Tool-Using Reinforcement Learning to Weak LLMs
por: Chen, Fu, et al.
Publicado: (2025)

AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
por: Wu, Shirley, et al.
Publicado: (2024)

MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning
por: Qian, Hongjin, et al.
Publicado: (2025)

Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding
por: Guo, Ruohao, et al.
Publicado: (2023)

MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation
por: Li, Rumeng, et al.
Publicado: (2019)

ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning
por: Wan, Ziyu, et al.
Publicado: (2025)

PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play
por: Fang, Wei, et al.
Publicado: (2025)

Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
por: Zhang, Yilang, et al.
Publicado: (2026)

Prolonging Tool Life: Learning Skillful Use of General-purpose Tools through Lifespan-guided Reinforcement Learning
por: Wu, Po-Yen, et al.
Publicado: (2025)

Neuromodulated Meta-Learning
por: Wang, Jingyao, et al.
Publicado: (2024)

A Multi-directional Meta-Learning Framework for Class-Generalizable Anomaly Detection
por: Roy, Padmaksha, et al.
Publicado: (2026)

MetaCD: A Meta Learning Framework for Cognitive Diagnosis based on Continual Learning
por: Wu, Jin, et al.
Publicado: (2025)

Hacking Task Confounder in Meta-Learning
por: Wang, Jingyao, et al.
Publicado: (2023)

Tool Unlearning for Tool-Augmented LLMs
por: Cheng, Jiali, et al.
Publicado: (2025)

GRAFT: Graph-Tokenized LLMs for Tool Planning
por: Gao, Xinyi, et al.
Publicado: (2026)

Towards Task Sampler Learning for Meta-Learning
por: Wang, Jingyao, et al.
Publicado: (2023)

Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
por: Acikgoz, Emre Can, et al.
Publicado: (2026)

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
por: Wu, Xixi, et al.
Publicado: (2026)

MetaRM: Shifted Distributions Alignment via Meta-Learning
por: Dou, Shihan, et al.
Publicado: (2024)

GraphTool-Instruction: Revolutionizing Graph Reasoning in LLMs through Decomposed Subtask Instruction
por: Wang, Rongzheng, et al.
Publicado: (2024)

CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision
por: Lu, Yifei, et al.
Publicado: (2025)

Bayesian Meta-Learning for Improving Generalizability of Health Prediction Models With Similar Causal Mechanisms
por: Wharrie, Sophie, et al.
Publicado: (2023)

ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning
por: Feng, Zihao, et al.
Publicado: (2025)

Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
por: Chu, Kexin, et al.
Publicado: (2026)