This repository serves as a curated list of research papers focused on Large Language Model (LLM) based agents. It aims to provide a comprehensive and categorized resource for researchers, engineers, and practitioners interested in the rapidly evolving field of AI agents, offering a structured overview of methodologies, applications, and challenges.

How It Works

The repository categorizes papers across a wide spectrum of LLM agent research, including core techniques like planning, memory, and feedback mechanisms, as well as various application domains and system-level considerations such as multi-agent systems, benchmarks, and safety. This structured approach allows users to efficiently navigate and discover relevant literature within specific sub-fields of LLM agent development.

Quick Start & Requirements

This repository is a curated list of papers and does not require installation or execution. It serves as a reference guide.

Highlighted Details

• Extensive categorization of LLM agent research, covering over 50 distinct sub-topics.
• Regularly updated with recent publications, reflecting the fast-paced nature of the field.
• Links to associated papers and code are provided where available, facilitating deeper exploration.
• Includes recommendations for other related paper lists for broader coverage.

Maintenance & Community

The repository is actively maintained, with recent updates noted in April 2025. It also references other community-driven paper lists, indicating a collaborative effort within the research community.

Licensing & Compatibility

The repository itself is a collection of links and does not have specific licensing terms beyond standard open-source practices for code and data. Compatibility is with any system that can access web links.

Limitations & Caveats

As a curated list, the repository's content is limited to what has been identified and added by its maintainers. It does not provide direct access to the papers themselves, only links to them.