@inproceedings{sara-etal-2026-multi,
title = "Multi-turn Conversational {AI} from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges",
author = "Sara, Syeda Faiza Ahmed and
Sheikh Ali, Zien and
Hassan Bhatti, Hunzalah and
Alam, Firoj and
Chowdhury, Shammur Absar",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2467/",
pages = "53068--53105",
ISBN = "979-8-89176-462-0",
abstract = "Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses, switch topics, and introduce new evidence while expecting systems to preserve context across turns. This makes multi-turn dialogue a distinct challenge requiring systems to maintain and update memory, ground responses across modalities, tools, and external knowledge, and adapt across languages and cultures. This study reviews ***multi-turn conversational AI*** across text-only dialogue, AudioLLMs and speech-native systems, multimodal and omni-modal systems, and tool-augmented agents. We organize the literature around *datasets* and *benchmarks*, *modeling paradigms*, *training strategies*, *evaluation setups*, and *cross-cutting challenges*. Our analysis shows that support for multiple modalities has advanced faster than the ability to sustain coherent interaction across a session. Despite stronger capabilities to perceive, speak, and act across modalities, current systems still struggle with persistent memory, cross-turn grounding, full-duplex interaction, robust evaluation, and cultural alignment. We conclude with a research agenda for systems that can remember, revise, ground, speak, listen, act, and adapt across turns, modalities, and cultures. ([https://github.com/faiza-sfa/multiturn-conversational-ai-survey](https://github.com/faiza-sfa/multiturn-conversational-ai-survey))"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sara-etal-2026-multi">
<titleInfo>
<title>Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Syeda</namePart>
<namePart type="given">Faiza</namePart>
<namePart type="given">Ahmed</namePart>
<namePart type="family">Sara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zien</namePart>
<namePart type="family">Sheikh Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hunzalah</namePart>
<namePart type="family">Hassan Bhatti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</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>Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses, switch topics, and introduce new evidence while expecting systems to preserve context across turns. This makes multi-turn dialogue a distinct challenge requiring systems to maintain and update memory, ground responses across modalities, tools, and external knowledge, and adapt across languages and cultures. This study reviews ***multi-turn conversational AI*** across text-only dialogue, AudioLLMs and speech-native systems, multimodal and omni-modal systems, and tool-augmented agents. We organize the literature around *datasets* and *benchmarks*, *modeling paradigms*, *training strategies*, *evaluation setups*, and *cross-cutting challenges*. Our analysis shows that support for multiple modalities has advanced faster than the ability to sustain coherent interaction across a session. Despite stronger capabilities to perceive, speak, and act across modalities, current systems still struggle with persistent memory, cross-turn grounding, full-duplex interaction, robust evaluation, and cultural alignment. We conclude with a research agenda for systems that can remember, revise, ground, speak, listen, act, and adapt across turns, modalities, and cultures. ([https://github.com/faiza-sfa/multiturn-conversational-ai-survey](https://github.com/faiza-sfa/multiturn-conversational-ai-survey))</abstract>
<identifier type="citekey">sara-etal-2026-multi</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2467/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>53068</start>
<end>53105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
%A Sara, Syeda Faiza Ahmed
%A Sheikh Ali, Zien
%A Hassan Bhatti, Hunzalah
%A Alam, Firoj
%A Chowdhury, Shammur Absar
%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 sara-etal-2026-multi
%X Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses, switch topics, and introduce new evidence while expecting systems to preserve context across turns. This makes multi-turn dialogue a distinct challenge requiring systems to maintain and update memory, ground responses across modalities, tools, and external knowledge, and adapt across languages and cultures. This study reviews ***multi-turn conversational AI*** across text-only dialogue, AudioLLMs and speech-native systems, multimodal and omni-modal systems, and tool-augmented agents. We organize the literature around *datasets* and *benchmarks*, *modeling paradigms*, *training strategies*, *evaluation setups*, and *cross-cutting challenges*. Our analysis shows that support for multiple modalities has advanced faster than the ability to sustain coherent interaction across a session. Despite stronger capabilities to perceive, speak, and act across modalities, current systems still struggle with persistent memory, cross-turn grounding, full-duplex interaction, robust evaluation, and cultural alignment. We conclude with a research agenda for systems that can remember, revise, ground, speak, listen, act, and adapt across turns, modalities, and cultures. ([https://github.com/faiza-sfa/multiturn-conversational-ai-survey](https://github.com/faiza-sfa/multiturn-conversational-ai-survey))
%U https://aclanthology.org/2026.findings-emnlp.2467/
%P 53068-53105
Markdown (Informal)
[Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges](https://aclanthology.org/2026.findings-emnlp.2467/) (Sara et al., Findings 2026)
ACL
- Syeda Faiza Ahmed Sara, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Firoj Alam, and Shammur Absar Chowdhury. 2026. Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 53068–53105, Budapest, Hungary. Association for Computational Linguistics.