@inproceedings{lee-etal-2026-beyond,
title = "Beyond {M}arkovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval",
author = "Lee, Dohyeon and
Jeong, Yeonseok and
Hwang, Seung-won",
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.1728/",
pages = "37266--37280",
ISBN = "979-8-89176-390-6",
abstract = "Reasoning-intensive information retrieval uses large language models to solve complex queries via multi-step reasoning. However, existing methods have critical limitations. Chain-of-Thought (CoT) approaches suffer from inefficiency, while state-based methods, despite better token efficiency, often fall into reasoning cycles that trap the query refinement process. To address these issues, we propose Episodic Memory for Retrieval (EMR), which enhances the state-based framework with an episodic memory. This module stores the full history of prior states for a query, allowing the model to avoid repetition of such cycles. Experiments on the BRIGHT benchmark show that EMR consistently outperforms both CoT and state-based baselines. Moreover, it is highly token-efficient, reducing token usage by 72{\%} on average. Our results show that episodic memory is an effective and token-efficient mechanism for reasoning-intensive retrieval. The gains also generalize across different base models and stay efficient in terms of end-to-end latency. The code is available in https://github.com/ldilab/EMR."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-beyond">
<titleInfo>
<title>Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dohyeon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeonseok</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</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>Reasoning-intensive information retrieval uses large language models to solve complex queries via multi-step reasoning. However, existing methods have critical limitations. Chain-of-Thought (CoT) approaches suffer from inefficiency, while state-based methods, despite better token efficiency, often fall into reasoning cycles that trap the query refinement process. To address these issues, we propose Episodic Memory for Retrieval (EMR), which enhances the state-based framework with an episodic memory. This module stores the full history of prior states for a query, allowing the model to avoid repetition of such cycles. Experiments on the BRIGHT benchmark show that EMR consistently outperforms both CoT and state-based baselines. Moreover, it is highly token-efficient, reducing token usage by 72% on average. Our results show that episodic memory is an effective and token-efficient mechanism for reasoning-intensive retrieval. The gains also generalize across different base models and stay efficient in terms of end-to-end latency. The code is available in https://github.com/ldilab/EMR.</abstract>
<identifier type="citekey">lee-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1728/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>37266</start>
<end>37280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval
%A Lee, Dohyeon
%A Jeong, Yeonseok
%A Hwang, Seung-won
%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 lee-etal-2026-beyond
%X Reasoning-intensive information retrieval uses large language models to solve complex queries via multi-step reasoning. However, existing methods have critical limitations. Chain-of-Thought (CoT) approaches suffer from inefficiency, while state-based methods, despite better token efficiency, often fall into reasoning cycles that trap the query refinement process. To address these issues, we propose Episodic Memory for Retrieval (EMR), which enhances the state-based framework with an episodic memory. This module stores the full history of prior states for a query, allowing the model to avoid repetition of such cycles. Experiments on the BRIGHT benchmark show that EMR consistently outperforms both CoT and state-based baselines. Moreover, it is highly token-efficient, reducing token usage by 72% on average. Our results show that episodic memory is an effective and token-efficient mechanism for reasoning-intensive retrieval. The gains also generalize across different base models and stay efficient in terms of end-to-end latency. The code is available in https://github.com/ldilab/EMR.
%U https://aclanthology.org/2026.acl-long.1728/
%P 37266-37280
Markdown (Informal)
[Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval](https://aclanthology.org/2026.acl-long.1728/) (Lee et al., ACL 2026)
ACL