<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-proevent">
    <titleInfo>
        <title>ProEvent: An Event-centric Benchmark for Proactive Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Guanzhen</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liangming</namePart>
        <namePart type="family">Pan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Leye</namePart>
        <namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Proactive agents are expected to anticipate user needs and provide autonomous assistance by perceiving environmental context without explicit instructions. A fundamental capability of such agents is to identify and track users’ upcoming events, enabling continuous and event-specific assistance. For example, by recording the time and location of a planned hike, an agent can deliver weather reminders in advance or provide navigation support before departure. However, existing works on proactive agents largely overlook event-centric assistance, and the open-ended nature of proactive assistance poses challenges for reliable evaluation.\par To bridge these gaps, we introduce ProEvent, the first event-centric benchmark designed to assess an agent’s ability to proactively maintain a user’s timetable based on ongoing instant messaging chats. ProEvent provides synthesized yet realistic chats that consider the dynamic interaction among users, concurrent chat threads, and noise in the real world, and evaluates proactive agents on response timing, single-step response correctness, and multi-step response correctness. Experiments on eight LLMs and pipelines reveal that current agents frequently overact and struggle with event cancellation. Notably, even the state-of-the-art GPT-5.1 provides redundant assistance in 30% of cases and achieves only 26.7% recall in event cancellation scenarios. Further qualitative analysis reveals fundamental limitations of current LLMs as proactive agents, particularly in detecting implicit events and reasoning from the user’s first-person perspective.</abstract>
    <identifier type="citekey">li-etal-2026-proevent</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1472/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>31322</start>
            <end>31336</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ProEvent: An Event-centric Benchmark for Proactive Agents
%A Li, Guanzhen
%A Pan, Liangming
%A Wang, Leye
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F li-etal-2026-proevent
%X Proactive agents are expected to anticipate user needs and provide autonomous assistance by perceiving environmental context without explicit instructions. A fundamental capability of such agents is to identify and track users’ upcoming events, enabling continuous and event-specific assistance. For example, by recording the time and location of a planned hike, an agent can deliver weather reminders in advance or provide navigation support before departure. However, existing works on proactive agents largely overlook event-centric assistance, and the open-ended nature of proactive assistance poses challenges for reliable evaluation.\par To bridge these gaps, we introduce ProEvent, the first event-centric benchmark designed to assess an agent’s ability to proactively maintain a user’s timetable based on ongoing instant messaging chats. ProEvent provides synthesized yet realistic chats that consider the dynamic interaction among users, concurrent chat threads, and noise in the real world, and evaluates proactive agents on response timing, single-step response correctness, and multi-step response correctness. Experiments on eight LLMs and pipelines reveal that current agents frequently overact and struggle with event cancellation. Notably, even the state-of-the-art GPT-5.1 provides redundant assistance in 30% of cases and achieves only 26.7% recall in event cancellation scenarios. Further qualitative analysis reveals fundamental limitations of current LLMs as proactive agents, particularly in detecting implicit events and reasoning from the user’s first-person perspective.
%U https://aclanthology.org/2026.findings-emnlp.1472/
%P 31322-31336

Markdown (Informal)

[ProEvent: An Event-centric Benchmark for Proactive Agents](https://aclanthology.org/2026.findings-emnlp.1472/) (Li et al., Findings 2026)

• ProEvent: An Event-centric Benchmark for Proactive Agents (Li et al., Findings 2026)

ACL

• Guanzhen Li, Liangming Pan, and Leye Wang. 2026. ProEvent: An Event-centric Benchmark for Proactive Agents. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 31322–31336, Budapest, Hungary. Association for Computational Linguistics.