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

ACL ARR 2026 January Submission3216 Authors

Keywords: rag, mcts, long document, passage retrieval, dense retrieval, document representation, re-ranking

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.

Paper Type: Long

Research Area: Information Extraction and Retrieval

Research Area Keywords: passage retrieval, dense retrieval, document representation, re-ranking

Contribution Types: NLP engineering experiment, Data analysis

Languages Studied: English

Submission Number: 3216