This repository is a curated list of papers focused on multi-agent systems, particularly those leveraging Large Language Models (LLMs). It serves researchers and practitioners interested in the rapidly evolving field of AI agents that collaborate and interact to solve complex problems. The collection aims to democratize knowledge in this area, fostering advancements in AI-driven automation and intelligence.

How It Works

The repository organizes papers into categories such as "Multi-Agent Collaboration & System Design," "Multi-Agent Frameworks & Benchmarks," and domain-specific applications like "Software Engineering" and "Healthcare." Each entry typically includes the paper title, authors, publication venue, and a link to the PDF. The collection highlights key research trends and foundational works in multi-agent LLM systems.

Quick Start & Requirements

This is a curated list of research papers, not a software library. No installation or specific requirements are needed to browse the content.

Highlighted Details

• Extensive categorization of papers covering core concepts, frameworks, and diverse application domains.
• Includes foundational papers and recent advancements in multi-agent LLM research.
• Provides direct links to research papers for easy access.
• Covers a wide range of topics from agent collaboration and reasoning to specific applications in software engineering, healthcare, and robotics.

Maintenance & Community

The repository is maintained by the Swarms Team. A Discord community is available for engagement.

Licensing & Compatibility

The repository itself is a collection of links to research papers. The licensing of the individual papers is determined by their respective publishers.

Limitations & Caveats

As a curated list, the repository's content is limited to the papers that have been added. The quality and focus of the collection depend on the maintainers' selection criteria.