@inproceedings{tang-etal-2026-memoryrewardbench,
title = "{M}emory{R}eward{B}ench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models",
author = "Tang, Zecheng and
Ji, Baibei and
Sun, Ruoxi and
Wang, Haitian and
Li, Juntao and
Zhang, Min",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2574/",
pages = "58484--58516",
ISBN = "979-8-89176-459-0",
abstract = "With the surge of AI-powered real-world applications, large language models (LLMs) increasingly adopt memory-centric mechanisms to handle multi-turn interactive tasks. Under this paradigm, intermediate processing trajectories, i.e., memory, are central to ensuring LLMs' faithfulness and effectiveness. Scalable evaluation of the memory management process serves as the cornerstone for further enhancing model performance. Yet, appropriate evaluators for the assessment of memory are currently lacking. Thus, in this work, we seek to employ reward models (RMs) as evaluators and introduce MemoryRewardBench, the first benchmark to systematically study the capability of RMs in assessing LLM memory management processes. MemoryRewardBench covers both long-form comprehension and generation tasks that simulate real-world multi-turn interaction scenarios, featuring 10 distinct settings with different memory management patterns. Evaluations on 13 cutting-edge RMs indicate a diminishing performance gap between open-source and proprietary models, with newer-generation models consistently outperforming their predecessors regardless of parameter count. Additionally, we reveal the fundamental limitations of RMs in evaluating LLMs' memory."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2026-memoryrewardbench">
<titleInfo>
<title>MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zecheng</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baibei</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruoxi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</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>With the surge of AI-powered real-world applications, large language models (LLMs) increasingly adopt memory-centric mechanisms to handle multi-turn interactive tasks. Under this paradigm, intermediate processing trajectories, i.e., memory, are central to ensuring LLMs’ faithfulness and effectiveness. Scalable evaluation of the memory management process serves as the cornerstone for further enhancing model performance. Yet, appropriate evaluators for the assessment of memory are currently lacking. Thus, in this work, we seek to employ reward models (RMs) as evaluators and introduce MemoryRewardBench, the first benchmark to systematically study the capability of RMs in assessing LLM memory management processes. MemoryRewardBench covers both long-form comprehension and generation tasks that simulate real-world multi-turn interaction scenarios, featuring 10 distinct settings with different memory management patterns. Evaluations on 13 cutting-edge RMs indicate a diminishing performance gap between open-source and proprietary models, with newer-generation models consistently outperforming their predecessors regardless of parameter count. Additionally, we reveal the fundamental limitations of RMs in evaluating LLMs’ memory.</abstract>
<identifier type="citekey">tang-etal-2026-memoryrewardbench</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2574/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>58484</start>
<end>58516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
%A Tang, Zecheng
%A Ji, Baibei
%A Sun, Ruoxi
%A Wang, Haitian
%A Li, Juntao
%A Zhang, Min
%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 tang-etal-2026-memoryrewardbench
%X With the surge of AI-powered real-world applications, large language models (LLMs) increasingly adopt memory-centric mechanisms to handle multi-turn interactive tasks. Under this paradigm, intermediate processing trajectories, i.e., memory, are central to ensuring LLMs’ faithfulness and effectiveness. Scalable evaluation of the memory management process serves as the cornerstone for further enhancing model performance. Yet, appropriate evaluators for the assessment of memory are currently lacking. Thus, in this work, we seek to employ reward models (RMs) as evaluators and introduce MemoryRewardBench, the first benchmark to systematically study the capability of RMs in assessing LLM memory management processes. MemoryRewardBench covers both long-form comprehension and generation tasks that simulate real-world multi-turn interaction scenarios, featuring 10 distinct settings with different memory management patterns. Evaluations on 13 cutting-edge RMs indicate a diminishing performance gap between open-source and proprietary models, with newer-generation models consistently outperforming their predecessors regardless of parameter count. Additionally, we reveal the fundamental limitations of RMs in evaluating LLMs’ memory.
%U https://aclanthology.org/2026.emnlp-main.2574/
%P 58484-58516
Markdown (Informal)
[MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models](https://aclanthology.org/2026.emnlp-main.2574/) (Tang et al., EMNLP 2026)
ACL