SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

• URL: http://arxiv.org/abs/2508.04700v1
• Date: Wed, 06 Aug 2025 17:58:46 GMT
• Title: SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
• Authors: Zeyi Sun, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, Jiaqi Wang,
• Abstract summary: We propose SEAgent, an agentic self-evolving framework enabling computer-use agents to evolve through interactions with unfamiliar software.<n>We validate the effectiveness of SEAgent across five novel software environments within OS-World.<n>Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA.
• Score: 71.82719117238307
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software, particularly in scenarios lacking human annotations. To address this challenge, we propose SEAgent, an agentic self-evolving framework enabling CUAs to autonomously evolve through interactions with unfamiliar software. Specifically, SEAgent empowers computer-use agents to autonomously master novel software environments via experiential learning, where agents explore new software, learn through iterative trial-and-error, and progressively tackle auto-generated tasks organized from simple to complex. To achieve this goal, we design a World State Model for step-wise trajectory assessment, along with a Curriculum Generator that generates increasingly diverse and challenging tasks. The agent's policy is updated through experiential learning, comprised of adversarial imitation of failure actions and Group Relative Policy Optimization (GRPO) on successful ones. Furthermore, we introduce a specialist-to-generalist training strategy that integrates individual experiential insights from specialist agents, facilitating the development of a stronger generalist CUA capable of continuous autonomous evolution. This unified agent ultimately achieves performance surpassing ensembles of individual specialist agents on their specialized software. We validate the effectiveness of SEAgent across five novel software environments within OS-World. Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA, i.e., UI-TARS.

Related papers

• SEA: Self-Evolution Agent with Step-wise Reward for Computer Use [6.056153018209402]
  We propose the Self-Evolution Agent (SEA) for computer use, and to develop this agent, we propose creative methods in data generation, reinforcement learning, and model enhancement.<n>Based on our proposed innovation of data generation, training strategy, and enhancement, we get the Selfevolution Agent (SEA) for computer use with only 7B parameters.
  arXiv  Detail & Related papers  (2025-08-06T02:57:22Z)
• UI-Evol: Automatic Knowledge Evolving for Computer Use Agents [19.978272700123004]
  We propose UI-Evol, a plug-and-play module for autonomous GUI knowledge evolution.<n> UI-Evol consists of two stages: a Retrace Stage that extracts faithful objective action sequences from actual agent-environment interactions, and a Critique Stage that refines existing knowledge by comparing these sequences against external references.<n>Our results demonstrate that UI-Evol not only significantly boosts task performance but also addresses a previously overlooked issue of high behavioral standard deviation in computer use agents.
  arXiv  Detail & Related papers  (2025-05-28T04:32:05Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Agent S: An Open Agentic Framework that Uses Computers Like a Human [31.16046798529319]
  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.
  arXiv  Detail & Related papers  (2024-10-10T17:43:51Z)
• Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents [44.34340798542]
  Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities. We propose a framework that combines guided Monte Carlo Tree Search (MCTS) search with a self-critique mechanism and iterative fine-tuning on agent interactions.
  arXiv  Detail & Related papers  (2024-08-13T20:52:13Z)
• 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)
• Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution [92.84441068115517]
  Investigate-Consolidate-Exploit (ICE) is a novel strategy for enhancing the adaptability and flexibility of AI agents. ICE promotes the transfer of knowledge between tasks for genuine self-evolution. Our experiments on the XAgent framework demonstrate ICE's effectiveness, reducing API calls by as much as 80%.
  arXiv  Detail & Related papers  (2024-01-25T07:47:49Z)
• Experiential Co-Learning of Software-Developing Agents [83.34027623428096]
  Large language models (LLMs) have brought significant changes to various domains, especially in software development. We introduce Experiential Co-Learning, a novel LLM-agent learning framework. Experiments demonstrate that the framework enables agents to tackle unseen software-developing tasks more effectively.
  arXiv  Detail & Related papers  (2023-12-28T13:50:42Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)

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.