@inproceedings{li-etal-2026-locomo,
title = "Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for {LLM} Agents",
author = "Li, Yifei and
Guo, Weidong and
Zhang, Lingling and
Xu, Rongman and
Huang, Muye and
Liu, Hui and
Xu, Lijiao and
Xu, Yu and
Liu, Jun",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1150/",
pages = "25085--25100",
ISBN = "979-8-89176-390-6",
abstract = "Long-term conversational memory is a core capability for LLM-baseddialogue systems, yet existing benchmarks and evaluation protocolsprimarily focus on surface-level factual recall.In realistic interactions, appropriate responses often depend onimplicit constraints such as user state, goals, or values that are notexplicitly queried later.To evaluate this setting, we introduce \textbf{LoCoMo-Plus}, a benchmarkfor assessing cognitive memory under cue{--}trigger semantic disconnect,where models must retain and apply latent constraints across longconversational contexts.We further show that conventional string-matching metrics and explicittask-type prompting are misaligned with such scenarios, and propose aunified evaluation framework based on constraint consistency.Experiments across diverse backbone models, retrieval-based methods, andmemory systems demonstrate that cognitive memory remains challenging andreveals failures not captured by existing benchmarks.Our code and evaluation framework are publicly available at https://github.com/xjtuleeyf/Locomo-Plus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-locomo">
<titleInfo>
<title>Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weidong</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingling</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongman</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muye</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijiao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Long-term conversational memory is a core capability for LLM-baseddialogue systems, yet existing benchmarks and evaluation protocolsprimarily focus on surface-level factual recall.In realistic interactions, appropriate responses often depend onimplicit constraints such as user state, goals, or values that are notexplicitly queried later.To evaluate this setting, we introduce LoCoMo-Plus, a benchmarkfor assessing cognitive memory under cue–trigger semantic disconnect,where models must retain and apply latent constraints across longconversational contexts.We further show that conventional string-matching metrics and explicittask-type prompting are misaligned with such scenarios, and propose aunified evaluation framework based on constraint consistency.Experiments across diverse backbone models, retrieval-based methods, andmemory systems demonstrate that cognitive memory remains challenging andreveals failures not captured by existing benchmarks.Our code and evaluation framework are publicly available at https://github.com/xjtuleeyf/Locomo-Plus.</abstract>
<identifier type="citekey">li-etal-2026-locomo</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1150/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>25085</start>
<end>25100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
%A Li, Yifei
%A Guo, Weidong
%A Zhang, Lingling
%A Xu, Rongman
%A Huang, Muye
%A Liu, Hui
%A Xu, Lijiao
%A Xu, Yu
%A Liu, Jun
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F li-etal-2026-locomo
%X Long-term conversational memory is a core capability for LLM-baseddialogue systems, yet existing benchmarks and evaluation protocolsprimarily focus on surface-level factual recall.In realistic interactions, appropriate responses often depend onimplicit constraints such as user state, goals, or values that are notexplicitly queried later.To evaluate this setting, we introduce LoCoMo-Plus, a benchmarkfor assessing cognitive memory under cue–trigger semantic disconnect,where models must retain and apply latent constraints across longconversational contexts.We further show that conventional string-matching metrics and explicittask-type prompting are misaligned with such scenarios, and propose aunified evaluation framework based on constraint consistency.Experiments across diverse backbone models, retrieval-based methods, andmemory systems demonstrate that cognitive memory remains challenging andreveals failures not captured by existing benchmarks.Our code and evaluation framework are publicly available at https://github.com/xjtuleeyf/Locomo-Plus.
%U https://aclanthology.org/2026.acl-long.1150/
%P 25085-25100
Markdown (Informal)
[Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents](https://aclanthology.org/2026.acl-long.1150/) (Li et al., ACL 2026)
ACL
- Yifei Li, Weidong Guo, Lingling Zhang, Rongman Xu, Muye Huang, Hui Liu, Lijiao Xu, Yu Xu, and Jun Liu. 2026. Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25085–25100, San Diego, California, United States. Association for Computational Linguistics.