<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-lifelong">
    <titleInfo>
        <title>Lifelong Intent Discovery: A Continual Learning Protocol and Method</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Peng</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Xia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bang</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>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>Discovering new intents is crucial for many systems to adapt to evolving users’ needs, making it inherently a continual process. However, most related studies have not explored such continual learning scenarios for new intent discovery. To bridge this research gap, we formalize the Continual Open-Stream Intent Discovery (COSID) task, which requires simultaneous detection of historical intents and discovery of new ones from hybrid streaming data. Our central contribution is a configurable open-stream dataset construction protocol that transforms a static intent dataset into a stream of temporally partitioned datasets, as well as a set of evaluation metrics for the COSID task. We further propose the Continual Intent Discovery Agent (CIDA) for the task, a memory-augmented agent that screens the incoming stream, clusters new-intents’ samples, and employs an LLM for intent abstraction and memory expansion. Experiments on the ClincCL and BankCL data streams constructed according to our protocol validate both the protocol expressiveness and agent superiority over existing baselines.</abstract>
    <identifier type="citekey">chen-etal-2026-lifelong</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.705/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>16286</start>
            <end>16314</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Lifelong Intent Discovery: A Continual Learning Protocol and Method
%A Chen, Peng
%A Xia, Yu
%A Wang, Bang
%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 chen-etal-2026-lifelong
%X Discovering new intents is crucial for many systems to adapt to evolving users’ needs, making it inherently a continual process. However, most related studies have not explored such continual learning scenarios for new intent discovery. To bridge this research gap, we formalize the Continual Open-Stream Intent Discovery (COSID) task, which requires simultaneous detection of historical intents and discovery of new ones from hybrid streaming data. Our central contribution is a configurable open-stream dataset construction protocol that transforms a static intent dataset into a stream of temporally partitioned datasets, as well as a set of evaluation metrics for the COSID task. We further propose the Continual Intent Discovery Agent (CIDA) for the task, a memory-augmented agent that screens the incoming stream, clusters new-intents’ samples, and employs an LLM for intent abstraction and memory expansion. Experiments on the ClincCL and BankCL data streams constructed according to our protocol validate both the protocol expressiveness and agent superiority over existing baselines.
%U https://aclanthology.org/2026.emnlp-main.705/
%P 16286-16314

Markdown (Informal)

[Lifelong Intent Discovery: A Continual Learning Protocol and Method](https://aclanthology.org/2026.emnlp-main.705/) (Chen et al., EMNLP 2026)

• Lifelong Intent Discovery: A Continual Learning Protocol and Method (Chen et al., EMNLP 2026)

ACL

• Peng Chen, Yu Xia, and Bang Wang. 2026. Lifelong Intent Discovery: A Continual Learning Protocol and Method. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 16286–16314, Budapest, Hungary. Association for Computational Linguistics.