<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-weng-2025-researstudio">
    <titleInfo>
        <title>ResearStudio: A Human-intervenable Framework for Building Controllable Deep Research Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Linyi</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yixuan</namePart>
        <namePart type="family">Weng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="family">Habernal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Peter</namePart>
            <namePart type="family">Schulam</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jörg</namePart>
            <namePart type="family">Tiedemann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-334-0</identifier>
    </relatedItem>
    <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,” and 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. We will release the full code, protocol, and evaluation scripts to encourage further work on safe and controllable research agents upon acceptance.</abstract>
    <identifier type="citekey">yang-weng-2025-researstudio</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-demos.69/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>896</start>
            <end>905</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ResearStudio: A Human-intervenable Framework for Building Controllable Deep Research Agents
%A Yang, Linyi
%A Weng, Yixuan
%Y Habernal, Ivan
%Y Schulam, Peter
%Y Tiedemann, Jörg
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-334-0
%F yang-weng-2025-researstudio
%X 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,” and 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. We will release the full code, protocol, and evaluation scripts to encourage further work on safe and controllable research agents upon acceptance.
%U https://aclanthology.org/2025.emnlp-demos.69/
%P 896-905

Markdown (Informal)

[ResearStudio: A Human-intervenable Framework for Building Controllable Deep Research Agents](https://aclanthology.org/2025.emnlp-demos.69/) (Yang & Weng, EMNLP 2025)

• ResearStudio: A Human-intervenable Framework for Building Controllable Deep Research Agents (Yang & Weng, EMNLP 2025)

ACL

• Linyi Yang and Yixuan Weng. 2025. ResearStudio: A Human-intervenable Framework for Building Controllable Deep Research Agents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 896–905, Suzhou, China. Association for Computational Linguistics.