A curated list of papers, tools, and benchmarks on computer-use agents: systems that let LLMs operate computers through terminals or graphical interfaces.
We organize this collection into two families:
- Terminal / CLI-Based Agents interact with computers through text interfaces: shell commands, file I/O, and code execution. This category spans five stages of development: code completion, chat assistants, autonomous coding agents, general-purpose sandbox agents, and personal AI assistants.
- GUI-Based Agents perceive and act on graphical interfaces through mouse clicks, keyboard input, and screen observation. We cover web agents, desktop/OS agents, and mobile agents, each with distinct perception strategies and challenges.
Note: This is a preliminary collection and is by no means exhaustive. Many important papers and tools are likely missing. If you know of work that should be included, please open a PR or issue. Contributions of all kinds are welcome!
We also wrote a short report discussing the development and architecture of these systems: report (PDF).
Contributions welcome! Please open a PR.
| Name | Year | Type | Links |
|---|
| Devin | 2024 | Product | Website |
| Claude Code | 2025 | Product | Docs |
| Codex CLI | 2025 | Product | GitHub |
| Gemini CLI | 2025 | Product | GitHub |
| Name | Year | Type | Links |
|---|
| Cursor Agent Mode | 2025 | Product | Website |
| Windsurf (Codeium) | 2025 | Product | Website |
| Name | Year | Type | Links |
|---|
| Mind2Web | 2023 | Paper + Data | Paper · GitHub |
| SeeAct | 2024 | Paper + Code | Paper · GitHub |
| WebVoyager | 2024 | Paper + Code | Paper |
| WebArena | 2023 | Benchmark + Paper | Paper · GitHub |
| Browser Use | 2025 | Open Source | GitHub |
| Operator (OpenAI) | 2025 | Product | Blog |
| Project Mariner (Google) | 2025 | Product | Blog |
| BrowserTrace | 2026 | Open Source Tool | GitHub |
| Agent QA | 2026 | Source-Available Tool | GitHub |
| ClawBench | 2026 | Benchmark + Paper | Paper · GitHub · Live |
| Name | Year | Type | Links |
|---|
| Computer Use (Anthropic) | 2024 | API | Blog |
| CogAgent | 2024 | Paper + Code | Paper · GitHub |
| ScreenAgent | 2024 | Paper | Paper |
| UFO (Microsoft) | 2024 | Paper + Code | Paper · GitHub |
| Set-of-Mark (SoM) | 2023 | Paper | Paper |
| OmniParser | 2024 | Paper + Code | Paper · GitHub |
| OS-Copilot | 2024 | Paper + Code | Paper |
| UI-TARS (ByteDance) | 2025 | Paper | Paper |
| UI-TARS-2 | 2025 | Paper | Paper |
| axcli | 2026 | Open Source | GitHub |
| Name | Year | Type | Links |
|---|
| AppAgent | 2024 | Paper + Code | Paper |
| Mobile-Agent-v3 | 2025 | Paper + Code | Paper |
| Name | Year | Links |
|---|
| ReAct: Synergizing Reasoning and Acting in Language Models | 2023 | Paper |
| Toolformer: Language Models Can Teach Themselves to Use Tools | 2023 | Paper |
| Codex: Evaluating Large Language Models Trained on Code | 2021 | Paper |
| GPT-4 Technical Report | 2023 | Paper |
| Plan-and-Solve Prompting | 2023 | Paper |
| AdaPlanner: Adaptive Planning from Feedback | 2023 | Paper |
| Tree of Thoughts | 2023 | Paper |
| LLM Debate: Improving Factuality through Multiagent Debate | 2024 | Paper |
PRs welcome! When adding an entry, please include:
- Name, year, and type (Paper / Product / Open Source)
- Links to paper (arXiv preferred), code (GitHub), and website
MIT
If you find this list helpful, please give it a ⭐!
@misc{cheng2026awesomecomputeruseagents,
title={Awesome Computer-Use Agents},
author={Cheng, Daixuan},
year={2026},
howpublished={\url{https://github.com/cdxeve/awesome-computer-use-agents}},
}