<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kodandaram-etal-2026-yet">
    <titleInfo>
        <title>Are We There Yet? Assessing Computer-Use Agents for Blind Users’ Accessible Interaction with Desktop Applications</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Satwik</namePart>
        <namePart type="given">Ram</namePart>
        <namePart type="family">Kodandaram</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Monalika</namePart>
        <namePart type="given">Padma</namePart>
        <namePart type="family">Reddy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaojun</namePart>
        <namePart type="family">Bi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiawei</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">I</namePart>
        <namePart type="family">Ramakrishnan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vikas</namePart>
        <namePart type="family">Ashok</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Computer-use agents are emerging as a paradigm for agentic human-AI interaction, combining language reasoning with multimodal interface grounding to operate GUIs. Yet their effectiveness for blind screen-reader users in real-world desktop workflows remains unclear. We present a three-week diary study with 8 blind users using OLLA, a screen-reader accessible CUA prototype, collecting 1,258commands across 12 applications with screenshots, UI trees, model responses, and action traces. We evaluate GPT-5 during deployment and re-execute the same commands with four additional models. GPT-5 achieved the highest success rate at 52.5%. Trace analysis reveals grounding, planning, constraint-tracking, and termination failures, while interviews reveal beyond-automation needs.</abstract>
    <identifier type="citekey">kodandaram-etal-2026-yet</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1763/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>40189</start>
            <end>40209</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Are We There Yet? Assessing Computer-Use Agents for Blind Users’ Accessible Interaction with Desktop Applications
%A Kodandaram, Satwik Ram
%A Reddy, Monalika Padma
%A Bi, Xiaojun
%A Zhou, Jiawei
%A Ramakrishnan, I.
%A Ashok, Vikas
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F kodandaram-etal-2026-yet
%X Computer-use agents are emerging as a paradigm for agentic human-AI interaction, combining language reasoning with multimodal interface grounding to operate GUIs. Yet their effectiveness for blind screen-reader users in real-world desktop workflows remains unclear. We present a three-week diary study with 8 blind users using OLLA, a screen-reader accessible CUA prototype, collecting 1,258commands across 12 applications with screenshots, UI trees, model responses, and action traces. We evaluate GPT-5 during deployment and re-execute the same commands with four additional models. GPT-5 achieved the highest success rate at 52.5%. Trace analysis reveals grounding, planning, constraint-tracking, and termination failures, while interviews reveal beyond-automation needs.
%U https://aclanthology.org/2026.emnlp-main.1763/
%P 40189-40209

Markdown (Informal)

[Are We There Yet? Assessing Computer-Use Agents for Blind Users’ Accessible Interaction with Desktop Applications](https://aclanthology.org/2026.emnlp-main.1763/) (Kodandaram et al., EMNLP 2026)

• Are We There Yet? Assessing Computer-Use Agents for Blind Users’ Accessible Interaction with Desktop Applications (Kodandaram et al., EMNLP 2026)

ACL

• Satwik Ram Kodandaram, Monalika Padma Reddy, Xiaojun Bi, Jiawei Zhou, I. Ramakrishnan, and Vikas Ashok. 2026. Are We There Yet? Assessing Computer-Use Agents for Blind Users’ Accessible Interaction with Desktop Applications. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 40189–40209, Budapest, Hungary. Association for Computational Linguistics.