awesome llm powered agent

Report Abuse

Basic Information

This repository is a curated, community-driven collection of resources about LLM-powered agents. It collects papers, open-source repositories, benchmarks, surveys, tutorials, perspectives and related links that document research and engineering around autonomous and multi-agent systems driven by large language models. The README organizes material into topical sections such as Autonomous Task Solver, Multi-Agent Cooperation, Framework & Open-Source, Applications (Web Agents, RL Agents, Robotics & Embodied AI, Gaming & Role-Playing and others), Trustworthy agents, Benchmarks and Surveys. It highlights prominent papers and projects and annotates notable entries. The project is intended as an exhaustive reference for people studying or building LLM agents and it explicitly invites contributions via pull requests, issues and suggestions. The README notes the repo is not under active maintenance and contains many papers appearing before October 2023 with further updates added afterward.

Links

Categorization

App Details

Features
A structured, annotated index of LLM-agent literature and software. Sections group resources by theme such as reasoning and planning, multi-agent cooperation, frameworks, applications and trustworthiness. Papers include badges and annotations for high-impact or peer-reviewed work. The list links reported code and project pages when available and enumerates popular open-source projects and frameworks, with examples like Auto-GPT, LangChain, GPT Engineer, MetaGPT, BabyAGI and others shown under Open-Source Projects. The repo also catalogs benchmarks, surveys and tutorials and offers a Perspectives and Other Related Sources section. An Acknowledgement section credits contributors. The README contains permalinks to each subsection, badges for license and contribution guidance, and explicit instructions for submitting additions via PRs.
Use Cases
The collection is a single entry point for researchers, engineers and informed readers to discover foundational and recent work on LLM-powered agents. It saves time by grouping papers, code repos, frameworks, benchmarks and tutorials by topic and by surfacing prominent open-source projects and evaluated benchmarks. Readers can use it to perform literature reviews, find implementations and demos, compare frameworks, explore application domains such as web automation, robotics, RL and gaming, and identify surveys and tutorials to get up to speed. The repository also helps locate code links and project pages for reproducibility and follow-up experiments. Users are encouraged to contribute missing papers or repos, though the README cautions that the list is not under active maintenance and may be incomplete.

Please fill the required fields*