Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Linyi, Weng, Yixuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.12194
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918212209213440
author Yang, Linyi
Weng, Yixuan
author_facet Yang, Linyi
Weng, Yixuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12194
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
Yang, Linyi
Weng, Yixuan
Artificial Intelligence
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.
title ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2510.12194