Agent S: An Open Agentic Framework that Uses Computers Like a Human

• URL: http://arxiv.org/abs/2410.08164v1
• Date: Thu, 10 Oct 2024 17:43:51 GMT
• Title: Agent S: An Open Agentic Framework that Uses Computers Like a Human
• Authors: Saaket Agashe, Jiuzhou Han, Shuyu Gan, Jiachen Yang, Ang Li, Xin Eric Wang,
• Abstract summary: We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI) Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces.
• Score: 31.16046798529319
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces. To this end, Agent S introduces experience-augmented hierarchical planning, which learns from external knowledge search and internal experience retrieval at multiple levels, facilitating efficient task planning and subtask execution. In addition, it employs an Agent-Computer Interface (ACI) to better elicit the reasoning and control capabilities of GUI agents based on Multimodal Large Language Models (MLLMs). Evaluation on the OSWorld benchmark shows that Agent S outperforms the baseline by 9.37% on success rate (an 83.6% relative improvement) and achieves a new state-of-the-art. Comprehensive analysis highlights the effectiveness of individual components and provides insights for future improvements. Furthermore, Agent S demonstrates broad generalizability to different operating systems on a newly-released WindowsAgentArena benchmark. Code available at https://github.com/simular-ai/Agent-S.

Related papers

• SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation [89.24729958546168]
  We present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents. SPA-Bench offers three key contributions: A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines. A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption.
  arXiv  Detail & Related papers  (2024-10-19T17:28:48Z)
• ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents [0.0]
  ClickAgent is a novel framework for building autonomous agents. In ClickAgent, the MLLM handles reasoning and action planning, while a separate UI location model identifies the relevant UI elements on the screen. Our evaluation was conducted on both an Android smartphone emulator and an actual Android smartphone, using the task success rate as the key metric for measuring agent performance.
  arXiv  Detail & Related papers  (2024-10-09T14:49:02Z)
• Turn Every Application into an Agent: Towards Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents [40.86728610906313]
  AXIS is a novel LLM-based agents framework that prioritizes actions through application programming interfaces (APIs) over user interface actions. Our experiments on Office Word demonstrate that AXIS reduces task completion time by 65%-70% and cognitive workload by 38%-53%, while maintaining accuracy of 97%-98% compare to humans. It also explores the possibility of turning every applications into agents, paving the way towards an agent-centric operating system (Agent OS)
  arXiv  Detail & Related papers  (2024-09-25T17:58:08Z)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence [79.5316642687565]
  Existing multi-agent frameworks often struggle with integrating diverse capable third-party agents. We propose the Internet of Agents (IoA), a novel framework that addresses these limitations. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control.
  arXiv  Detail & Related papers  (2024-07-09T17:33:24Z)
• CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only [21.054681757006385]
  We propose an agent that perceives its environment solely through screenshot images. By leveraging the reasoning capability of the Large Language Models, we eliminate the need for large-scale human demonstration data. Agent achieves an average success rate of 94.5% on MiniWoB++ and an average task score of 62.3 on WebShop.
  arXiv  Detail & Related papers  (2024-06-11T05:21:20Z)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [79.07755560048388]
  SWE-agent is a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively.
  arXiv  Detail & Related papers  (2024-05-06T17:41:33Z)
• WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks? [83.19032025950986]
  We study the use of large language model-based agents for interacting with software via web browsers. WorkArena is a benchmark of 33 tasks based on the widely-used ServiceNow platform. BrowserGym is an environment for the design and evaluation of such agents.
  arXiv  Detail & Related papers  (2024-03-12T14:58:45Z)
• AgentScope: A Flexible yet Robust Multi-Agent Platform [66.64116117163755]
  AgentScope is a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment.
  arXiv  Detail & Related papers  (2024-02-21T04:11:28Z)
• TaskBench: Benchmarking Large Language Models for Task Automation [82.2932794189585]
  We introduce TaskBench, a framework to evaluate the capability of large language models (LLMs) in task automation. Specifically, task decomposition, tool selection, and parameter prediction are assessed. Our approach combines automated construction with rigorous human verification, ensuring high consistency with human evaluation.
  arXiv  Detail & Related papers  (2023-11-30T18:02:44Z)
• A Zero-Shot Language Agent for Computer Control with Structured Reflection [19.526676887048662]
  Large language models (LLMs) have shown increasing capacity at planning and executing a high-level goal in a live computer environment. To perform a task, recent works often require a model to learn from trace examples of the task via either supervised learning or few/many-shot prompting. We approach this problem with a zero-shot agent that requires no given expert traces.
  arXiv  Detail & Related papers  (2023-10-12T21:53:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.