@inproceedings{tao-etal-2026-momoka,
title = "Momoka-{RAG}: {MCTS}-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation",
author = "Tao, Wenyu and
Xing, Xiaofen and
Li, Zeliang and
Xu, Xiangmin",
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.183/",
pages = "3749--3773",
ISBN = "979-8-89176-395-1",
abstract = "Existing frameworks remain trapped in a passive and mechanical approach in constructing knowledge structure, which only allows them to uncover superficial associations between chunks while lacking proactive exploration of deeper semantic relationships among them. To address the aforementioned issues, we propose **Momoka-RAG** (MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation). It employs the **Momoka-Map** to utilize Monte Carlo Tree Search (MCTS) to proactively uncover connections among chunks and construct optimal semantic information paths with the objective of completing semantic relationships. On this basis, the **Momoka-Trail Retriever** further expands and filters the chunk candidate pool to retrieve the chunks most relevant to the query. Experiments on datasets including Dragonball, SQUAD, NFCORPUS, SCI-DOCS, HotpotQA, and TriviaQA demonstrate that for long-document retrieval tasks, our framework achieves higher precision while maintaining competitive recall compared to other RAG frameworks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tao-etal-2026-momoka">
<titleInfo>
<title>Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenyu</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaofen</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeliang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangmin</namePart>
<namePart type="family">Xu</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>Existing frameworks remain trapped in a passive and mechanical approach in constructing knowledge structure, which only allows them to uncover superficial associations between chunks while lacking proactive exploration of deeper semantic relationships among them. To address the aforementioned issues, we propose **Momoka-RAG** (MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation). It employs the **Momoka-Map** to utilize Monte Carlo Tree Search (MCTS) to proactively uncover connections among chunks and construct optimal semantic information paths with the objective of completing semantic relationships. On this basis, the **Momoka-Trail Retriever** further expands and filters the chunk candidate pool to retrieve the chunks most relevant to the query. Experiments on datasets including Dragonball, SQUAD, NFCORPUS, SCI-DOCS, HotpotQA, and TriviaQA demonstrate that for long-document retrieval tasks, our framework achieves higher precision while maintaining competitive recall compared to other RAG frameworks.</abstract>
<identifier type="citekey">tao-etal-2026-momoka</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.183/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3749</start>
<end>3773</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation
%A Tao, Wenyu
%A Xing, Xiaofen
%A Li, Zeliang
%A Xu, Xiangmin
%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 tao-etal-2026-momoka
%X Existing frameworks remain trapped in a passive and mechanical approach in constructing knowledge structure, which only allows them to uncover superficial associations between chunks while lacking proactive exploration of deeper semantic relationships among them. To address the aforementioned issues, we propose **Momoka-RAG** (MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation). It employs the **Momoka-Map** to utilize Monte Carlo Tree Search (MCTS) to proactively uncover connections among chunks and construct optimal semantic information paths with the objective of completing semantic relationships. On this basis, the **Momoka-Trail Retriever** further expands and filters the chunk candidate pool to retrieve the chunks most relevant to the query. Experiments on datasets including Dragonball, SQUAD, NFCORPUS, SCI-DOCS, HotpotQA, and TriviaQA demonstrate that for long-document retrieval tasks, our framework achieves higher precision while maintaining competitive recall compared to other RAG frameworks.
%U https://aclanthology.org/2026.findings-acl.183/
%P 3749-3773
Markdown (Informal)
[Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation](https://aclanthology.org/2026.findings-acl.183/) (Tao et al., Findings 2026)
ACL