Awesome-Papers-Autonomous-Agent
An actively maintained collection of research papers on building autonomous agents, organized separately for reinforcement-learning-based agents and large-language-model-based agents.
Awesome-Papers-Autonomous-Agent is a curated, actively maintained collection of research papers on autonomous agents, defined as systems that perceive an environment, take actions toward a goal, and improve through learning or acquired knowledge. It separates the field into two traditions: reinforcement-learning-based agents and large-language-model-based agents, rather than treating them as one topic.
Papers are grouped by research direction, including instruction following, building agents around world models, using language as knowledge, generalizing across tasks, continual learning, combining reinforcement learning with language models, multimodal agents, multi-agent cooperation, benchmarks and datasets, and applications. A separate section collects surveys of the field.
It is a documentation-only repository with no accompanying code, and welcomes issues pointing out papers it has missed.