mlsanityData to 7 Oct 2026

Monte Carlo Tree Search with Reasoning Path Refinement for Small Language Models in Conversational Text-to-NoSQL

arXiv 2602.12574 ↗First posted 13 Feb 2026cs.DB cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

NoSQL databases have been widely adopted in big data analytics, geospatial applications, and healthcare services, due to their flexibility and scalability. However, querying NoSQL databases requires specialized technical expertise, creating a high barrier for users. While recent studies have explored text-to-NoSQL problem, they primarily focus on single-turn interactions, ignoring the conversational nature of real-world queries. To bridge this gap, we introduce the Conversational Text-to-NoSQL task, which generates NoSQL queries given a natural language question, a NoSQL database, and the dialogue history. To address this task, we propose Stage-MCTS, a framework that endows small language models (SLMs) with NoSQL-specific reasoning capabilities by formulating query generation as a search problem. The framework employs Monte Carlo Tree Search (MCTS) guided by a rule-based reward to produce stepwise reasoning data, followed by progressive supervised fine-tuning (SFT) and self-training strategies. We further construct CoNoSQL, a cross-domain dataset with over 2,000 dialogues and 150 databases, to support evaluation. Experiments demonstrate that our approach outperforms state-of-the-art large reasoning models, improving execution value match (EVM) accuracy by up to 7.93%.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 14 of its 84 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

14 of 84 references.

References · 14

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2024GPT-4o System Cardcited by 4,467
  4. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  5. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  6. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  7. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  8. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  9. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  10. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
  11. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  12. 2024CodeR: Issue Resolving with Multi-Agent and Task Graphscited by 89
2 more
  1. 2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 17
  2. 2025Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL
  2. 2025MCTS-KBQA: Monte Carlo Tree Search with Information Gain Rewards for Knowledge Base Question Answering
  3. 2025Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
  4. 2026IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models
  5. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
  6. 2025SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
  7. 2026Querying Structured Data Through Natural Language Using Language Models
  8. 2025LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models