@inproceedings{man-etal-2026-reasoning,
title = "Reasoning with Memory: Adaptive Information Management for Retrieval-Augmented Generation",
author = "Man, Hieu and
Tal, Ro-ee and
Kumar, Abhishek and
Cho, Jaejin and
Hsu, Benjamin",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1834/",
pages = "36825--36841",
ISBN = "979-8-89176-395-1",
abstract = "Multi-hop reasoning remains a fundamental challenge for Retrieval-Augmented Generation (RAG) systems. Recent approaches{---}from adaptive retrieval to agentic pipelines{---}struggle to maintain coherent intermediate reasoning states as chains grow longer. We introduce State-Aware RAG, a framework that addresses this limitation through an explicit working memory that serves as a dynamic cognitive workspace for reasoning. Our modular architecture features a lightweight, trainable extractor that learns to actively filter, consolidate, and update this working memory via a novel Path-Outcome Dual Reward paradigm, which balances local coherence with global strategy. The retriever and generator remain frozen, enabling plug-and-play flexibility. Experiments on eight QA benchmarks demonstrate state-of-the-art results, on average achieving +8.6{\%} over the best memory-augmented baseline and +9.3{\%} over the best RL-enhanced baseline. Our architecture generalizes seamlessly to stronger generators and retrievers without retraining, establishing dynamic memory management as a critical yet underexplored dimension for advancing RAG systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="man-etal-2026-reasoning">
<titleInfo>
<title>Reasoning with Memory: Adaptive Information Management for Retrieval-Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hieu</namePart>
<namePart type="family">Man</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ro-ee</namePart>
<namePart type="family">Tal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaejin</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Hsu</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Multi-hop reasoning remains a fundamental challenge for Retrieval-Augmented Generation (RAG) systems. Recent approaches—from adaptive retrieval to agentic pipelines—struggle to maintain coherent intermediate reasoning states as chains grow longer. We introduce State-Aware RAG, a framework that addresses this limitation through an explicit working memory that serves as a dynamic cognitive workspace for reasoning. Our modular architecture features a lightweight, trainable extractor that learns to actively filter, consolidate, and update this working memory via a novel Path-Outcome Dual Reward paradigm, which balances local coherence with global strategy. The retriever and generator remain frozen, enabling plug-and-play flexibility. Experiments on eight QA benchmarks demonstrate state-of-the-art results, on average achieving +8.6% over the best memory-augmented baseline and +9.3% over the best RL-enhanced baseline. Our architecture generalizes seamlessly to stronger generators and retrievers without retraining, establishing dynamic memory management as a critical yet underexplored dimension for advancing RAG systems.</abstract>
<identifier type="citekey">man-etal-2026-reasoning</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1834/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>36825</start>
<end>36841</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reasoning with Memory: Adaptive Information Management for Retrieval-Augmented Generation
%A Man, Hieu
%A Tal, Ro-ee
%A Kumar, Abhishek
%A Cho, Jaejin
%A Hsu, Benjamin
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F man-etal-2026-reasoning
%X Multi-hop reasoning remains a fundamental challenge for Retrieval-Augmented Generation (RAG) systems. Recent approaches—from adaptive retrieval to agentic pipelines—struggle to maintain coherent intermediate reasoning states as chains grow longer. We introduce State-Aware RAG, a framework that addresses this limitation through an explicit working memory that serves as a dynamic cognitive workspace for reasoning. Our modular architecture features a lightweight, trainable extractor that learns to actively filter, consolidate, and update this working memory via a novel Path-Outcome Dual Reward paradigm, which balances local coherence with global strategy. The retriever and generator remain frozen, enabling plug-and-play flexibility. Experiments on eight QA benchmarks demonstrate state-of-the-art results, on average achieving +8.6% over the best memory-augmented baseline and +9.3% over the best RL-enhanced baseline. Our architecture generalizes seamlessly to stronger generators and retrievers without retraining, establishing dynamic memory management as a critical yet underexplored dimension for advancing RAG systems.
%U https://aclanthology.org/2026.findings-acl.1834/
%P 36825-36841
Markdown (Informal)
[Reasoning with Memory: Adaptive Information Management for Retrieval-Augmented Generation](https://aclanthology.org/2026.findings-acl.1834/) (Man et al., Findings 2026)
ACL