mlsanityData to 7 Oct 2026

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

arXiv 2503.04412 ↗First posted 6 Mar 2025cs.AIcited by 48

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated sampling (i.e., generating multiple candidate outputs) is a highly effective strategy, it does not leverage external feedback signals for refinement, which are often available in tasks like coding. In this work, we propose Adaptive Branching Monte Carlo Tree Search (AB-MCTS), a novel inference-time framework that generalizes repeated sampling with principled multi-turn exploration and exploitation. At each node in the search tree, AB-MCTS dynamically decides whether to "go wider" by expanding new candidate responses or "go deeper" by revisiting existing ones based on external feedback signals. We evaluate our method on complex coding and engineering tasks using frontier models. Empirical results show that AB-MCTS consistently outperforms both repeated sampling and standard MCTS, underscoring the importance of combining the response diversity of LLMs with multi-turn solution refinement for effective inference-time scaling. Code is available at https://github.com/SakanaAI/treequest .

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 35 of its 56 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

35 of 56 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Competitive Programming with Large Reasoning Models3 Feb
  2. 2025s1: Simple test-time scaling31 Jan
  3. 2025Evolving Deeper LLM Thinking17 Jan
  4. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions21 Nov
  5. 2024Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification5 Oct
  6. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models1 Aug
  7. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing18 Apr
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  9. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May
  11. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 24

  1. 2020Scaling Laws for Neural Language Modelscited by 6,411
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023Let's Verify Step by Stepcited by 3,598
  6. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  7. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  8. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  9. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  10. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  11. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  12. 2023Reasoning with Language Model is Planning with World Modelcited by 846
12 more
  1. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  2. 2025LIMO: Less is More for Reasoningcited by 488
  3. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 429
  4. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
  5. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  6. 2024Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Modelscited by 277
  7. 2024AlphaMath Almost Zero: Process Supervision without Processcited by 160
  8. 2024SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinementcited by 124
  9. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  10. 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoffcited by 50
  11. 2024Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoningcited by 38
  12. 2024CodeTree: Agent-guided Tree Search for Code Generation with Large Language Modelscited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 36.

48 papers.

Sort:

By area:

  1. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 215
  2. 2025Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Spacecited by 40
  3. 2025Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoningcited by 32
  4. 2025The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Computecited by 11
  5. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  6. 2025Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectoriescited by 10
  7. 2026Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agentscited by 10
  8. 2026From Scale to Speed: Adaptive Test-Time Scaling for Image Editingcited by 7
  9. 2026LLMs Improving LLMs: Agentic Discovery for Test-Time Scalingcited by 7
  10. 2025LLM-First Search: Self-Guided Exploration of the Solution Spacecited by 5
  11. 2025Making, not Taking, the Best of Ncited by 4
  12. 2026The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoningcited by 4
36 more
  1. 2026EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learningcited by 4
  2. 2026Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agentscited by 4
  3. 2026Training AI Scientists to Replicate Researchcited by 4
  4. 2025Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancementcited by 3
  5. 2026MARTI-MARS2: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generationcited by 3
  6. 2026ATLAS: Agentic Test-time Learning-to-Allocate Scalingcited by 3
  7. 2025Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Modelscited by 2
  8. 2026Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolutioncited by 2
  9. 2026Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Searchcited by 2
  10. 2026UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branchingcited by 2
  11. 2026Exploration and Exploitation Errors Are Measurable for Language Model Agentscited by 2
  12. 2026OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agentscited by 2
  13. 2026Self-Improving Language Models with Bidirectional Evolutionary Searchcited by 2
  14. 2025MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learningcited by 1
  15. 2026SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generationcited by 1
  16. 2026Beyond the Node: Clade-level Selection for Efficient MCTS in Automatic Heuristic Designcited by 1
  17. 2026MARS2: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generationcited by 1
  18. 2026UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scalingcited by 1
  19. 2026Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiabilitycited by 1
  20. 2026Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routingcited by 1
  21. 2026Exploit More, Explore Smarter for Budget-Constrained Agentic Searchcited by 1
  22. 2026FluxLite: Inference-Time Proposal Control for Discrete Diffusion Modelscited by 1
  23. 2025Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoningcited by 0
  24. 2025Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Taskscited by 0
  25. 2026Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute Scalingcited by 0
  26. 2026Inference-Time Code Selection via Symbolic Equivalence Partitioningcited by 0
  27. 2026Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketchingcited by 0
  28. 2026REVES: REvision and VErification--Augmented Training for Test-Time Scalingcited by 0
  29. 2026Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loopcited by 0
  30. 2026Fork-Think with Confidencecited by 0
  31. 2026CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agentscited by 0
  32. 2026Efficiency Matters in Autonomous Researchcited by 0
  33. 2026GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoningcited by 0
  34. 2026Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneckcited by 0
  35. 2026Sampling via Decision-Flow: Training-Free Extraction of Improved Latent Reasoning Paths in Large Language Modelscited by 0
  36. 2026When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models
  2. 2025Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search
  3. 2026Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
  4. 2025Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective
  5. 2025Entropy-Gated Branching for Efficient Test-Time Reasoning
  6. 2025Optimal Stopping vs Best-of-N for Inference Time Optimization
  7. 2025A*-Decoding: Token-Efficient Inference Scaling
  8. 2025DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling