Awesome-Papers-Autonomous-Agent
VerifiedCurated collection of recent papers on autonomous AI agents.
What is Awesome-Papers-Autonomous-Agent?
Awesome-Papers-Autonomous-Agent is a maintained GitHub collection of academic papers exploring intelligent agents that act autonomously. It excludes classic RL agents and instead highlights modern RL variants alongside LLM-driven systems capable of goal achievement and ongoing adaptation.
The repo structures content with dedicated sections for surveys, RL topics such as instruction following and world models, and LLM topics including multimodal agents, multi-agent societies, benchmarks, and applications. Each entry links to arXiv or conference versions plus project pages when available.
It serves AI researchers, graduate students, and practitioners who need a single organized resource to track progress in autonomous agent design without sifting through scattered publications.
What you can build with Awesome-Papers-Autonomous-Agent
Track latest research
Quickly scan newly accepted papers from NeurIPS, ICML, and ICLR related to agent capabilities.
Explore specific topics
Jump to categorized lists covering multi-agent cooperation, continual learning, or task-specific LLM designs.
Find benchmarks and datasets
Locate evaluation resources and application-focused papers for building or comparing new agents.
Install Awesome-Papers-Autonomous-Agent
- 1Open the GitHub repository in your browser.
- 2Scroll to the Table of Contents and choose a category such as Surveys or LLM-based agent.
- 3Click any paper title to open the PDF or project page.
- 4Check the update history section for recently added conference papers.
- 5Star the repo and watch for new issues reporting missed papers.
Awesome-Papers-Autonomous-Agent: pros & cons
Pros
- +Well-organized taxonomy covering both RL and LLM agent research
- +Actively maintained with conference paper updates and project links
- +Includes dedicated survey section for quick overviews
- +Clear separation of topics like multi-agent systems and benchmarks
Cons
- –Contains only paper references, no code or runnable examples
- –Relies on external links that may become outdated
- –Scope limited to two agent paradigms, omitting other approaches
Frequently asked questions
No, the collection deliberately excludes classic RL agents and focuses on newer RL and LLM variants.
User reviews
Verified reviews from the community shape this listing's rating.
Loading reviews…
Similar agents
Other general-purpose options worth comparing.
