@inproceedings{wang-etal-2026-memory-makes,
title = "Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents",
author = "Wang, Yuxin and
Thomas, Paul and
Yu, Zhiwei and
Gao, Yuan and
Hassanpour, Saeed and
Vosoughi, Soroush and
Sim, Robert and
Craswell, Nick",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.30/",
pages = "378--401",
ISBN = "979-8-89176-478-1",
abstract = "Memory is a critical component of modern conversational systems. Prior research on memory mechanisms in RAG-based conversational systems has focused on how memory is stored and retrieved. However, less is known about how memories with different functional roles influence response quality, shape agents' responses across conversational contexts, and lead to distinct response behaviors. Existing evaluations are also largely reference-based, often missing response nuances that address users' preferences differently. In this work, we study the impact of different memory types on agent responses. We present a fine-grained taxonomy of conversational memory, classify retrieved memories by functional role, and design a user-centric evaluation framework that simulates user perspectives. Through comparative experiments on long-term datasets and frontier LLMs, our analysis reveals differentiated effects of memory: e.g., clarifying memory is associated with improved factual accuracy and constraint awareness, making responses more correct and personalized, while irrelevant memory reduces topic relevance and degrades constraint awareness. These findings show that, despite the power of frontier LLMs, different memory types can be leveraged to produce responses better aligned with a user{'}s stated constraints, and motivate further research in this direction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-memory-makes">
<titleInfo>
<title>Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saeed</namePart>
<namePart type="family">Hassanpour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soroush</namePart>
<namePart type="family">Vosoughi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Sim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nick</namePart>
<namePart type="family">Craswell</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 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</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">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>Memory is a critical component of modern conversational systems. Prior research on memory mechanisms in RAG-based conversational systems has focused on how memory is stored and retrieved. However, less is known about how memories with different functional roles influence response quality, shape agents’ responses across conversational contexts, and lead to distinct response behaviors. Existing evaluations are also largely reference-based, often missing response nuances that address users’ preferences differently. In this work, we study the impact of different memory types on agent responses. We present a fine-grained taxonomy of conversational memory, classify retrieved memories by functional role, and design a user-centric evaluation framework that simulates user perspectives. Through comparative experiments on long-term datasets and frontier LLMs, our analysis reveals differentiated effects of memory: e.g., clarifying memory is associated with improved factual accuracy and constraint awareness, making responses more correct and personalized, while irrelevant memory reduces topic relevance and degrades constraint awareness. These findings show that, despite the power of frontier LLMs, different memory types can be leveraged to produce responses better aligned with a user’s stated constraints, and motivate further research in this direction.</abstract>
<identifier type="citekey">wang-etal-2026-memory-makes</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.30/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>378</start>
<end>401</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents
%A Wang, Yuxin
%A Thomas, Paul
%A Yu, Zhiwei
%A Gao, Yuan
%A Hassanpour, Saeed
%A Vosoughi, Soroush
%A Sim, Robert
%A Craswell, Nick
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F wang-etal-2026-memory-makes
%X Memory is a critical component of modern conversational systems. Prior research on memory mechanisms in RAG-based conversational systems has focused on how memory is stored and retrieved. However, less is known about how memories with different functional roles influence response quality, shape agents’ responses across conversational contexts, and lead to distinct response behaviors. Existing evaluations are also largely reference-based, often missing response nuances that address users’ preferences differently. In this work, we study the impact of different memory types on agent responses. We present a fine-grained taxonomy of conversational memory, classify retrieved memories by functional role, and design a user-centric evaluation framework that simulates user perspectives. Through comparative experiments on long-term datasets and frontier LLMs, our analysis reveals differentiated effects of memory: e.g., clarifying memory is associated with improved factual accuracy and constraint awareness, making responses more correct and personalized, while irrelevant memory reduces topic relevance and degrades constraint awareness. These findings show that, despite the power of frontier LLMs, different memory types can be leveraged to produce responses better aligned with a user’s stated constraints, and motivate further research in this direction.
%U https://aclanthology.org/2026.groundlm-1.30/
%P 378-401
Markdown (Informal)
[Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents](https://aclanthology.org/2026.groundlm-1.30/) (Wang et al., GroundLM 2026)
ACL
- Yuxin Wang, Paul Thomas, Zhiwei Yu, Yuan Gao, Saeed Hassanpour, Soroush Vosoughi, Robert Sim, and Nick Craswell. 2026. Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents. In Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026), pages 378–401, Budapest, Hungary. Association for Computational Linguistics.