paper-with-me

Papers

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

2026-01-19 · Zheng Fang, Wolfgang Mayer, Zeyu Zhang, Jian Wang, Hong-Yu Zhang, Wanli Li, Zaiwen Feng arxiv

Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By selecting and integrating appropriate tools, LLMs extend their capabilities beyond pure language understanding to perform specialized functions. However, existing methods for tool selection often focus on limited tool sets and struggle to generalize to novel tools encountered in practical deployments. To address these challenges, we introduce a comprehensive dataset spanning 7 domains, containing 155 tools and 9,377 question-answer pairs, which simulates realistic integration scenarios. Additionally, we propose MetaToolAgent (MTA), a meta-learning approach designed to improve cross-tool generalization. Experimental results show that MTA significantly outperforms baseline methods on unseen tools, demonstrating its promise for building flexible and scalable systems that require dynamic tool coordination.

📄 PDF Abstract BibTeX arXiv:2601.12680

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models

2024-02-26 · Anchun Gui, Jian Li, Yong Dai, Nan Du 외

Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-source LLMs (e.g., ChatGPT) have demonst…

Decision MakingHallucinationIn-Context Learning

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning

2025-07-29 · Yifan Wei, Xiaoyan Yu, Yixuan Weng, Tengfei Pan 외 arxiv

Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporatin…

Reinforcement Learning

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation

2025-02-26 · Jie He, Jennifer Neville, Mengting Wan, Longqi Yang 외

Large Language Models (LLMs) can enhance their capabilities as AI assistants by integrating external tools, allowing them to access a wider range of information. While recent LLMs are typically fine-tuned with tool usage…

Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction

2026-01-19 · Xingjie Gao, Pengcheng Huang, Zhenghao Liu, Yukun Yan 외 arxiv

Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challenge when confronting novel or evolving to…

Reinforcement Learning

WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models

2024-07-02 · Kangyun Ning, Yisong Su, Xueqiang Lv, Yuanzhe Zhang 외

Although Large Language Models (LLMs) excel in NLP tasks, they still need external tools to extend their ability. Current research on tool learning with LLMs often assumes mandatory tool use, which does not always align …