mlsanityData to 7 Oct 2026

PathFinder: MCTS and LLM Feedback-based Path Selection for Multi-Hop Question Answering

arXiv 2512.05336 ↗First posted 5 Dec 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-hop question answering is a challenging task in which language models must reason over multiple steps to reach the correct answer. With the help of Large Language Models and their reasoning capabilities, existing systems are able to think and decompose an input question over multiple steps to analyze, retrieve, and reason. However, training-based approaches for this problem still suffer from LLM hallucinations and incorrect reasoning paths that hinder performance. Hence, we propose PATHFINDER, an approach that: (i) uses Monte Carlo Tree Search to generate training path traces, (ii) improves training data quality by filtering erroneous and lengthy traces using sub-answer recall and LLM-as-a-judge verification, and (iii) reformulates sub-queries to handle failed retrieval cases. By following these steps, we demonstrate that PATHFINDER improves the performance of multi-hop QA over public benchmark datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 29 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

26 of 29 references.

References · 26

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2024Qwen2 Technical Reportcited by 2,076
  6. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  11. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  12. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
14 more
  1. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  2. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  3. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  4. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
  5. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  6. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 238
  7. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  8. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Modelscited by 41
  9. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Modelscited by 37
  10. 2025RaDeR: Reasoning-aware Dense Retrieval Modelscited by 27
  11. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Searchcited by 20
  12. 2024Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generationcited by 15
  13. 2024AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoningcited by 10
  14. 2025AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generationcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
  2. 2024Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models
  3. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge
  4. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
  5. 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
  6. 2025Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search
  7. 2022From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering
  8. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering