Elamur Research⌕
☰
home / papers / 2026 / Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation

Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation

Paper · 2026 · Wenyu Tao, Xiaofen Xing, Zeliang Li et al.

Summary

Momoka-RAG targets retrieval over long documents. In that setting, standard chunking breaks cross-paragraph context, and structure-building frameworks such as RAPTOR (clustering into summary trees) and GraphRAG (entity graphs) find only shallow, statistics-driven links between chunks. The authors argue these methods follow fixed rules rather than actively seeking the information a chunk lacks.

Their framework has two parts. Momoka-Map first splits a document with an LLM and attaches a global title to every chunk. It then treats each chunk as a node and runs Monte Carlo Tree Search to find paths of chunks that fill each other's semantic gaps. Because this search happens offline at indexing time, query-time latency stays low. The Momoka-Trail Retriever starts from similarity-based hits, enlarges the candidate set along the precomputed paths, and uses a Reranker to choose the final context.

Across six benchmarks, the authors report higher precision with competitive recall compared with other RAG frameworks. The method is plug-and-play and requires no training.

Key points

  • MCTS is applied during indexing rather than retrieval, unlike approaches such as MCTS-RAG, where each node is a retrieval step.
  • Retrieval works in three stages: static similarity search, then a Mixed-Granularity Expansion Strategy over the path model, then Reranker scoring.
  • Evaluation covers Dragonball, SQUAD, NFCORPUS, SCI-DOCS, HotpotQA and TriviaQA. Metrics include Recall@k, MRR@k, Precision@k, EIR@k, F1@k, METEOR, ROUGE-L, BLEU, latency, and Dragonball's LLM-judged Relevant/Irrelevant/Wrong scores.
  • Baselines are Late-Chunking, RAPTOR, Meta-Chunking-PPL/MSP and Dense X Retrieval. Momoka-RAG was tested on top of four chunkers: Fixed-Length, LLM-based, Meta-Chunking-MSP and Meta-Chunking-PPL. Hyperparameters were α=3, β=2, γ=δ=1.
  • The authors list two limitations. Paths cannot adapt to the specific query, and the method does not scale well to cross-document retrieval, since MCTS cost grows and position cues stop being meaningful.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksInformation Systems · 1,437 works

🧭 Topics 1Research subjects and languages the work is about.Information retrieval & search · 473 works

Cite

Cite as Wenyu Tao, Xiaofen Xing, Zeliang Li and Xiangmin Xu. 2026. Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.183

@inproceedings{tao2026momoka,
  title = {{Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation}},
  author = {Wenyu Tao, Xiaofen Xing, Zeliang Li and Xiangmin Xu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.183},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.183}
}

References

25 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Isabelle Augenstein, Timothy Baldwin, Meeyoung Cha, Tanmoy Chakraborty, Giovanni Luca Ciampaglia, David Corney, Renee DiResta, Emilio Ferrara, Scott Hale, Alon Halevy, Eduard Hovy, Heng Ji, Filippo Menczer, Ruben Miguez, Preslav Nakov, Dietram Scheufele, Shivam Sharma, and Giovanni Zagni. 2023. Fact… — Factuality Challenges in the Era of Large Language Models
  2. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, and 29 others. 2023. Qwen technical report. Preprint, arXiv:2309.16609.
  3. Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72, Ann Arbor, Michigan. Ass…
  4. Vera Boteva, Demian Gholipour, Artem Sokolov, and Stefan Riezler. 2016. A full-text learning to rank dataset for medical information retrieval. find
  5. Cameron B. Browne, Edward Powley, Daniel Whitehouse, Simon M. Lucas, Peter I. Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, and Simon Colton. 2012. A survey of monte carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games, 4(1):1… find
  6. Harrison Chase. 2024. Langchain: A framework for developing applications powered by language models. Accessed: 2024-12-13. find
  7. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2023. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. Preprint, arXiv:2309.07597.
  8. Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, and Dong Yu. 2024. Dense x retrieval: What retrieval granularity should we use? Preprint, arXiv:2312.06648.
  9. Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S. Weld. 2020. Specter: Document-level representation learning using citation-informed transformers. Preprint, arXiv:2004.07180.
  10. T. Cover and P. Hart. 2006. Nearest neighbor pattern classification. IEEE Trans. Inf. Theor., 13(1):21–27. find
  11. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  12. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. Preprint, arXiv:2404.16130. find
  13. Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, and Chao Huang. 2025. Lightrag: Simple and fast retrieval-augmented generation. Preprint, arXiv:2410.05779.
  14. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. Preprint, arXiv:1606.05250.
  15. Ellen M. Voorhees and Dawn M. Tice. 2000. The TREC-8 question answering track. In Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00), Athens, Greece. European Language Resources Association (ELRA).
  16. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. Preprint, arXiv:1809.09600.
  17. Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2025. Hipporag: Neurobiologically inspired long-term memory for large language models. Preprint, arXiv:2405.14831.
  18. Jihao Zhao, Zhiyuan Ji, Yuchen Feng, Pengnian Qi, Simin Niu, Bo Tang, Feiyu Xiong, and Zhiyu Li. 2024. Meta-chunking: Learning efficient text segmentation via logical perception. Preprint, arXiv:2410.12788. — [arXiv:2410.12788](https://arxiv.org/abs/2410.12788) find
  19. Michael Günther, Isabelle Mohr, Daniel James Williams, Bo Wang, and Han Xiao. 2024. Late chunking: Contextual chunk embeddings using long-context embedding models. Preprint, arXiv:2409.04701. — [arXiv:2409.04701](https://arxiv.org/abs/2409.04701) find
  20. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, and 3 others. 2025. A survey of large language models. Prepri…
  21. Yunhai Hu, Yilun Zhao, Chen Zhao, and Arman Cohan. 2025. Mcts-rag: Enhancing retrieval-augmented generation with monte carlo tree search. Preprint, arXiv:2503.20757. find
  22. Mandar Joshi, Eunsol Choi, Daniel S. Weld, and Luke Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. Preprint, arXiv:1705.03551.
  23. Kunlun Zhu, Yifan Luo, Dingling Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Ruobing Wang, Shuo Wang, Yishan Li, Nan Zhang, Xu Han, Zhiyuan Liu, and Maosong Sun. 2025. Rageval: Scenario specific rag evaluation dataset generation framework. Preprint, arXiv:2408.01262.
  24. Levente Kocsis and Csaba Szepesvari. 2006. Bandit based monte-carlo planning. In European Conference on Machine Learning. find
  25. A Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2021. Retrieval-augmented generation for knowledge-intensive nlp tasks. Preprint, arXiv:2005.11401.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tao-2026-momoka-rag-mcts-organized-mapping/