Autonomous Agents
A daily-updated list of research papers on autonomous LLM agents, each summarized in a few bullet points covering the paper's method, architecture, and evaluation.
Autonomous Agents is a running collection of research papers about autonomous agents built on large language models, updated daily and organized in chronological order by year.
Each entry names the paper and gives a short bullet-point summary of what it introduces, such as a new architecture, training pipeline, benchmark, or evaluation method, covering topics including agent memory systems, world models, multi-agent coordination, and agentic frameworks.
The repository is MIT licensed and is intended as a reading list for keeping up with agent research rather than as runnable software.