This repository is a curated collection of recent research papers on autonomous agents, specifically focusing on Reinforcement Learning (RL)-based and Large Language Model (LLM)-based agents. It aims to provide a comprehensive overview for researchers and practitioners interested in the advancements and methodologies within this rapidly evolving field.

How It Works

The collection categorizes papers into two primary types: RL-based agents and LLM-based agents, with further sub-classifications based on research topics such as instruction following, world models, language as knowledge, and multi-agent systems. This structured approach allows for easy navigation and understanding of the landscape of autonomous agent research, highlighting both traditional RL techniques and the emerging capabilities of LLMs.

Quick Start & Requirements

This is a curated list of research papers and does not have installation or execution requirements.

Highlighted Details

• Comprehensive categorization of papers into RL-based and LLM-based agents, with detailed sub-topics.
• Includes papers accepted by major conferences like NeurIPS, ICLR, and ICML.
• Provides links to project pages, GitHub repositories, and blog posts for many listed papers.
• Actively maintained with regular updates and encourages community contributions via issues.

Maintenance & Community

The repository is actively maintained, with recent updates noted for January and December 2024, and October/November 2023. The maintainers encourage users to open issues for missed papers.

Licensing & Compatibility

The repository itself does not specify a license, but it links to external research papers which will have their own respective licenses. Compatibility for commercial use or closed-source linking would depend on the licenses of the individual papers and their associated codebases.

Limitations & Caveats

As a curated list, the repository's content is limited to the papers that have been identified and added by the maintainers. The scope is focused on RL and LLM-based agents, excluding traditional RL agents.