paper-with-me

Papers

MetaTool: Facilitating Large Language Models to Master Tools with Meta-task Augmentation

2024-07-15 · Xiaohan Wang, Dian Li, Yilin Zhao, Sinbadliu, Hui Wang

Utilizing tools with Large Language Models (LLMs) is essential for grounding AI agents in real-world applications. The prevailing approach involves few-shot prompting with demonstrations or fine-tuning with expert annotations. However, mere in-context demonstrations may fail to cover sufficient knowledge for complex tools and tasks. Training on solution paths is also hindered by the high cost of expert annotations and generalizing to new tools. A core challenge of generalizable tool use lies in understanding the "meta", or fundamental natures of tools that are transferable across tasks, such as causality and constraints. In this paper, we present MetaTool, a novel tool learning methodology designed to generalize across any reusable toolset. Our approach incorporates a self-supervised augmentation technique derived from a series of meta-tasks. This involves predicting masked elements in the tool execution process. The self-supervised procedure enables scalable generation of high-quality QA data, which is handy for supervising tool understanding. By incorporating meta-task data into task-oriented training, our method significantly enhances the performance of open-source LLMs, achieving results comparable to ChatGPT in both tool-based planning and chatting scenarios. Through large-scale instruction tuning, the MetaTool model demonstrates impressive zero-shot generalizability on new tasks.

📄 PDF Abstract BibTeX arXiv:2407.12871

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

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

2026-01-19 · Zheng Fang, Wolfgang Mayer, Zeyu Zhang, Jian Wang 외 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 t…

MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use

2023-10-04 · Yue Huang, Jiawen Shi, Yuan Li, Chenrui Fan 외

Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. Recently, many studies have focused on the tool utilization ability of LLMs. They p…

Decision Making

Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference

2026-03-13 · Huamin Chen, Xunzhuo Liu, Junchen Jiang, Bowei He 외 arxiv

Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Outcome-Aware Tool Selection (OATS), which …

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

2024-10-10 · Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai 외

Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this proce…

Diversity

MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools

2025-10-28 · Wenhao Wang, Peizhi Niu, Zhao Xu, Zhaoyu Chen 외 arxiv

Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet their ability to utilize the rapidly expanding Model Contextual Protocol (MCP) ecosystem remains limited. Existing…