This repository serves as a curated collection of must-read papers on tool learning with foundation models, targeting researchers and practitioners in AI. It aims to provide a comprehensive overview of the rapidly evolving field, making key works more accessible and facilitating future development by organizing resources and highlighting important concepts.

How It Works

The repository categorizes papers based on their approach to tool learning, including "Tool-augmented Learning" and "Tool-oriented Learning." It also lists papers by application areas and provides a "Keywords Convention" to standardize the description of research works, focusing on abbreviations, utilized tools, and other critical information.

Quick Start & Requirements

This is a curated list of research papers and does not have a direct installation or execution command. All listed papers are available as preprints or published works, with links to PDFs and often associated code or project pages provided.

Highlighted Details

• Comprehensive list of papers on tool learning with foundation models, covering various approaches and applications.
• Includes links to PDFs, code repositories, and project pages for many listed works.
• Organizes research by sub-fields like Tool-augmented Learning and Tool-oriented Learning.
• Provides a standardized keyword convention for describing research contributions.

Maintenance & Community

The repository encourages community contributions to ensure its comprehensiveness. It lists contributors and acknowledges their efforts in building the resource.

Licensing & Compatibility

The repository itself does not appear to have a specific license mentioned, but it links to external research papers, each with its own licensing and distribution terms. Compatibility for commercial use would depend on the licenses of the individual papers and their associated code.

Limitations & Caveats

The list is a snapshot of the field and may not be exhaustive, as the repository explicitly welcomes community contributions to fill any gaps. The rapid pace of research means new papers are constantly emerging.