SEA: Self-Evolution Agent with Step-wise Reward for Computer Use

• URL: http://arxiv.org/abs/2508.04037v1
• Date: Wed, 06 Aug 2025 02:57:22 GMT
• Title: SEA: Self-Evolution Agent with Step-wise Reward for Computer Use
• Authors: Liang Tang, Shuxian Li, Yuhao Cheng, Yukang Huo, Zhepeng Wang, Yiqiang Yan, Kaer Huang, Yanzhe Jing, Tiaonan Duan,
• Abstract summary: 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.
• Score: 6.056153018209402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Computer use agent is an emerging area in artificial intelligence that aims to operate the computers to achieve the user's tasks, which attracts a lot of attention from both industry and academia. However, the present agents' performance is far from being used. In this paper, 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. Specifically, we first propose an automatic pipeline to generate the verifiable trajectory for training. And then, we propose efficient step-wise reinforcement learning to alleviate the significant computational requirements for long-horizon training. In the end, we propose the enhancement method to merge the grounding and planning ability into one model without any extra training. Accordingly, 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, which outperforms models with the same number of parameters and has comparable performance to larger ones. We will make the models' weight and related codes open-source in the future.

Related papers

• SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience [71.82719117238307]
  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.
  arXiv  Detail & Related papers  (2025-08-06T17:58:46Z)
• LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback [121.78866929908871]
  Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data.<n>We present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback.<n>Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive real-time feedback.
  arXiv  Detail & Related papers  (2025-06-02T22:36:02Z)
• MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability [106.35604230971396]
  Recent advancements in Agent techniques enable Large Language Models (LLMs) to autonomously utilize tools for retrieval, planning, and reasoning.<n>To further enhance the universal search capability of agents, we propose a novel pre-training framework, MaskSearch.<n>In the pre-training stage, we introduce the Retrieval Augmented Mask Prediction (RAMP) task, where the model learns to leverage search tools to fill masked spans.<n>After that, the model is trained on downstream tasks to achieve further improvement.
  arXiv  Detail & Related papers  (2025-05-26T17:58:50Z)
• To Train or Not to Train: Balancing Efficiency and Training Cost in Deep Reinforcement Learning for Mobile Edge Computing [15.079887992932692]
  We present a new algorithm to dynamically select when to train a Deep Reinforcement Learning (DRL) agent that allocates resources. Our method is highly general, as it can be directly applied to any scenario involving a training overhead.
  arXiv  Detail & Related papers  (2024-11-11T16:02:12Z)
• Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment [69.33930972652594]
  We propose a novel structural pruning approach to jointly learn the weights and structurally prune architectures of CNN models. The core element of our method is a Reinforcement Learning (RL) agent whose actions determine the pruning ratios of the CNN model's layers. We conduct the joint training and pruning by iteratively training the model's weights and the agent's policy.
  arXiv  Detail & Related papers  (2024-03-28T15:22:29Z)
• An Interactive Agent Foundation Model [49.77861810045509]
  We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-action prediction. We demonstrate the performance of our framework across three separate domains -- Robotics, Gaming AI, and Healthcare.
  arXiv  Detail & Related papers  (2024-02-08T18:58:02Z)
• TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System [14.019244136838017]
  TrainerAgent is a multi-agent framework including Task, Data, Model and Server agents. These agents analyze user-defined tasks, input data, and requirements (e.g., accuracy, speed), optimizing them from both data and model perspectives to obtain satisfactory models, and finally deploy these models as online service. This research presents a significant advancement in achieving desired models with increased efficiency and quality as compared to traditional model development.
  arXiv  Detail & Related papers  (2023-11-11T17:39:24Z)
• RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation [68.70755196744533]
  RoboGen is a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. Our work attempts to extract the extensive and versatile knowledge embedded in large-scale models and transfer them to the field of robotics.
  arXiv  Detail & Related papers  (2023-11-02T17:59:21Z)
• Orchestration of Emulator Assisted Mobile Edge Tuning for AI Foundation Models: A Multi-Agent Deep Reinforcement Learning Approach [10.47302625959368]
  We present a groundbreaking paradigm integrating Mobile Edge Computing with foundation models, specifically designed to enhance local task performance on user equipment (UE) Central to our approach is the innovative Emulator-Adapter architecture, segmenting the foundation model into two cohesive modules. We introduce an advanced resource allocation mechanism that is fine-tuned to the needs of the Emulator-Adapter structure in decentralized settings.
  arXiv  Detail & Related papers  (2023-10-26T15:47:51Z)

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.