Awesome LLM Agent Papers
An annotated, actively updated reading list of over 500 papers on LLM agents, organized by function such as planning, memory, tool use and safety, built as a companion to a survey paper.
This repository is a curated reading list on large language model agents, covering planning, memory, tool use, multi-agent coordination, benchmarks and safety, including prompt injection. It serves as a companion to a survey paper on LLM agents, collecting the references behind that paper plus newer work, and organizes them into ten sections that follow the survey's own structure.
Each entry carries a one-line note on what it contributes, its venue and year, and a link to an official implementation where one exists. A starter kit highlights ten papers worth reading first, and a separate, related list collects papers specifically on the agent loop itself, including open-source frameworks, coding harnesses, memory and sandbox infrastructure, and skill libraries.