mlsanityData to 14 Oct 2026

LiteSearch: Efficacious Tree Search for LLM

arXiv 2407.00320 ↗First posted 29 Jun 2024cs.CL cs.AI cs.LGcited by 31

Not on the map. Why?

Cited by 22 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources of greedy decoding due to wasteful search strategies, making them difficult to be deployed in practical applications. This study introduces a novel guided tree search algorithm with dynamic node selection and node-level exploration budget (maximum number of children) calculation to tackle this issue. By considering the search progress towards the final answer (history) and the guidance from a value network (future) trained without any step-wise annotations, our algorithm iteratively selects the most promising tree node before expanding it within the boundaries of the allocated computational budget. Experiments conducted on the GSM8K and TabMWP datasets demonstrate that our approach not only offers competitive performance but also enjoys significantly lower computational costs compared to baseline methods.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 29 Jun 2024.

Builds on

26 of 40 references.

References · 26

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2023Let's Verify Step by Stepcited by 3,789
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  9. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  10. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 625
  11. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 557
  12. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
14 more
  1. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 295
  2. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 196
  3. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  4. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizingcited by 125
  5. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 117
  6. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 110
  7. 2023Let's reward step by step: Step-Level reward model as the Navigators for Reasoningcited by 102
  8. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 97
  9. 2024MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Timecited by 41
  10. 2021Neural-Symbolic Solver for Math Word Problems with Auxiliary Taskscited by 38
  11. 2023GRACE: Discriminator-Guided Chain-of-Thought Reasoningcited by 35
  12. 2024FlowMind: Automatic Workflow Generation with LLMscited by 30
  13. 2024Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoningcited by 24
  14. 2024Self-Consistency Boosts Calibration for Math Reasoningcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 11; 2025: 18; 2026: 2.

31 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  3. 2024Tree Search for Language Model Agentscited by 151
  4. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTScited by 54
  5. 2024HunyuanProver: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Provingcited by 33
  6. 2024Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learningcited by 30
  7. 2025CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Modelscited by 29
  8. 2024RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generationcited by 26
  9. 2024Non-myopic Generation of Language Models for Reasoning and Planningcited by 26
  10. 2024Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehensioncited by 23
  11. 2024Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generationcited by 21
  12. 2025Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoningcited by 19
19 more
  1. 2025RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learningcited by 16
  2. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 15
  3. 2024BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Searchcited by 13
  4. 2025Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfallscited by 13
  5. 2025ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videoscited by 12
  6. 2025Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Studycited by 11
  7. 2025LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Informationcited by 8
  8. 2024C2: Scalable Auto-Feedback for LLM-based Chart Generationcited by 6
  9. 2025PATS: Process-Level Adaptive Thinking Mode Switchingcited by 6
  10. 2025Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTScited by 5
  11. 2025LLMPC: Large Language Model Predictive Controlcited by 4
  12. 2025How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilitiescited by 4
  13. 2026Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMscited by 4
  14. 2024Multi-Programming Language Ensemble for Code Generation in Large Language Modelcited by 3
  15. 2025Streaming Looking Ahead with Token-level Self-rewardcited by 2
  16. 2025Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioningcited by 2
  17. 2025Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Searchcited by 2
  18. 2025Reward Model Generalization for Compute-Aware Test-Time Reasoningcited by 0
  19. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LiTS: A Modular Framework for LLM Tree Search
  2. 2024Enhancing LLM Reasoning with Reward-guided Tree Search
  3. 2025Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs
  4. 2025LLM-First Search: Self-Guided Exploration of the Solution Space
  5. 2025Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey
  6. 2025MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
  7. 2025Dynamic Parallel Tree Search for Efficient LLM Reasoning
  8. 2024Interpretable Contrastive Monte Carlo Tree Search Reasoning