mlsanityData to 14 Oct 2026

MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search

arXiv 2503.20757 ↗First posted 26 Mar 2025cs.CLcited by 21

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

also in 1 more
Abstract (arXiv)

We introduce MCTS-RAG, a novel approach that enhances the reasoning capabilities of small language models on knowledge-intensive tasks by leveraging retrieval-augmented generation (RAG) to provide relevant context and Monte Carlo Tree Search (MCTS) to refine reasoning paths. MCTS-RAG dynamically integrates retrieval and reasoning through an iterative decision-making process. Unlike standard RAG methods, which typically retrieve information independently from reasoning and thus integrate knowledge suboptimally, or conventional MCTS reasoning, which depends solely on internal model knowledge without external facts, MCTS-RAG combines structured reasoning with adaptive retrieval. This integrated approach enhances decision-making, reduces hallucinations, and ensures improved factual accuracy and response consistency. The experimental results on multiple reasoning and knowledge-intensive datasets datasets (i.e., ComplexWebQA, GPQA, and FoolMeTwice) show that our method enables small-scale LMs to achieve performance comparable to frontier LLMs like GPT-4o by effectively scaling inference-time compute, setting a new standard for reasoning in small-scale models.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 29 of its 38 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

29 of 38 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  2. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement17 Dec
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 26

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  9. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  10. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  11. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  12. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
14 more
  1. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  2. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  3. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  4. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 344
  5. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  6. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  7. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 196
  8. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solverscited by 138
  9. 2025MMVU: Measuring Expert-Level Multi-Discipline Video Understandingcited by 137
  10. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  11. 2021Fool Me Twice: Entailment from Wikipedia Gamificationcited by 50
  12. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  13. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipelinecited by 27
  14. 2024SMART-RAG: Selection using Determinantal Matrices for Augmented Retrievalcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 13.

21 papers.

Sort:

By area:

  1. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 335
  2. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  3. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  4. 2025RaDeR: Reasoning-aware Dense Retrieval Modelscited by 27
  5. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answeringcited by 14
  6. 2025From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graphcited by 10
  7. 2026ProbeLLM: Automating Principled Diagnosis of LLM Failurescited by 9
  8. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrievalcited by 6
  9. 2026When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Controlcited by 3
  10. 2026SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generationcited by 1
  11. 2026PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflectioncited by 1
  12. 2026MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoningcited by 1
9 more
  1. 2025MSRS: Evaluating Multi-Source Retrieval-Augmented Generationcited by 0
  2. 2025PathFinder: MCTS and LLM Feedback-based Path Selection for Multi-Hop Question Answeringcited by 0
  3. 2026MARVEL: A Multi Agent-based Research Validator and Enabler using Large Language Modelscited by 0
  4. 2026RAG without Forgetting: Continual Query-Infused Key Memorycited by 0
  5. 2026RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigmcited by 0
  6. 2026Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAGcited by 0
  7. 2026DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answeringcited by 0
  8. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Modelscited by 0
  9. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnessescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
  2. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
  3. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
  4. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  5. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  6. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
  7. 2025Structure-Augmented Reasoning Generation
  8. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models