{"ID":2855578,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12194","arxiv_id":"2510.12194","title":"ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents","abstract":"Current deep-research agents run in a ''fire-and-forget'' mode: once started, they give users no way to fix errors or add expert knowledge during execution. We present ResearStudio, the first open-source framework that places real-time human control at its core. The system follows a Collaborative Workshop design. A hierarchical Planner-Executor writes every step to a live ''plan-as-document,'' a fast communication layer streams each action, file change, and tool call to a web interface. At any moment, the user can pause the run, edit the plan or code, run custom commands, and resume -- switching smoothly between AI-led, human-assisted and human-led, AI-assisted modes. In fully autonomous mode, ResearStudio achieves state-of-the-art results on the GAIA benchmark, surpassing systems like OpenAI's DeepResearch and Manus. These results show that strong automated performance and fine-grained human control can coexist. The full code, protocol, and evaluation scripts are available at https://github.com/ResearAI/ResearStudio. We will continue to update the repository to encourage further work on safe and controllable research agents. Our live demo is publicly accessible at http://ai-researcher.net:3000/. We support the development of DeepScientist, which can be accessed at https://github.com/ResearAI/DeepScientist.","short_abstract":"Current deep-research agents run in a ''fire-and-forget'' mode: once started, they give users no way to fix errors or add expert knowledge during execution. We present ResearStudio, the first open-source framework that places real-time human control at its core. The system follows a Collaborative Workshop design. A hie...","url_abs":"https://arxiv.org/abs/2510.12194","url_pdf":"https://arxiv.org/pdf/2510.12194v2","authors":"[\"Linyi Yang\",\"Yixuan Weng\"]","published":"2025-10-14T06:40:11Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","project_urls":"[\"http://ai-researcher.net:3000/\"]","has_code":false,"code_links":[{"ID":608265,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2855578,"paper_url":"https://arxiv.org/abs/2510.12194","paper_title":"ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents","repo_url":"https://github.com/ResearAI/ResearStudio","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":608266,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2855578,"paper_url":"https://arxiv.org/abs/2510.12194","paper_title":"ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents","repo_url":"https://github.com/ResearAI/DeepScientist","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}