REVIEW 29 cited by
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS), designed to enhance performance in complex mathematical reasoning tasks. Addressing the challenges of accuracy and reliability in LLMs, particularly in strategic and mathematical reasoning, MCTSr leverages systematic exploration and heuristic self-refine mechanisms to improve decision-making frameworks within LLMs. The algorithm constructs a Monte Carlo search tree through iterative processes of Selection, self-refine, self-evaluation, and Backpropagation, utilizing an improved Upper Confidence Bound (UCB) formula to optimize the exploration-exploitation balance. Extensive experiments demonstrate MCTSr's efficacy in solving Olympiad-level mathematical problems, significantly improving success rates across multiple datasets, including GSM8K, GSM Hard, MATH, and Olympiad-level benchmarks, including Math Odyssey, AIME, and OlympiadBench. The study advances the application of LLMs in complex reasoning tasks and sets a foundation for future AI integration, enhancing decision-making accuracy and reliability in LLM-driven applications.
Forward citations
Cited by 29 Pith papers
-
Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization
KernelPro combines LLM code generation, roofline-guided tool orchestration, and domain-adapted MCTS to produce GPU kernels that outperform prior automated and some hand-tuned baselines on KernelBench and VeOmni workloads.
-
Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
Introduces OPT* tasks and two training regimes (solver-guided online policy optimization with rank-based reward shaping and search-based offline RL) plus a theoretical link between search success and information extra...
-
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
TTT-RTL performs per-design test-time RL on an LLM policy with EDA-derived PPA rewards and an adaptive KL controller, reducing geometric-mean PPA product by 65.1% on RTLLM v2.0 and ADP by 59.4% on an industrial FPU unit.
-
Regulating Branch Parallelism in LLM Serving
TAPER regulates LLM branch parallelism by admitting extra branches opportunistically when predicted externality fits slack, delivering 1.48-1.77x higher goodput than eager or fixed-cap baselines on Qwen3-32B while kee...
-
On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
Parallel thinking in LLMs suffers from overscaling where fixed global budgets waste samples; LanBo predicts per-sample budgets from latent states to raise utilization without hurting accuracy.
-
Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning
Rewarding each parallel reasoning path by Monte-Carlo-Shapley marginal contribution, scored by a generative reward model, lifts Pass@16 on AIME24/AIME25/AMC23 by 4-90% relative over Parallel-R1 with a fifth of the tra...
-
Online Self-Calibration Against Hallucination in Vision-Language Models
OSCAR exploits the generative-discriminative gap in LVLMs to build online preference data with MCTS and dual-granularity rewards for DPO-based calibration, claiming SOTA hallucination reduction and improved multimodal...
-
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
A disagreement-guided routing framework dynamically selects among resolution, voting, and rewriting strategies for test-time scaling, delivering 3-7% accuracy gains with lower sampling cost on mathematical benchmarks.
-
Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
A Lagrangian-relaxation plus imitation-learning pipeline adaptively allocates test-time compute to LLMs, outperforming uniform baselines by up to 12.8% relative accuracy on MATH while staying within a fixed average budget.
-
ProbeLLM: Automating Principled Diagnosis of LLM Failures
An automated LLM probing pipeline using hierarchical Monte Carlo Tree Search, tool-based verification, and failure clustering to discover structured failure modes beyond static benchmarks.
-
Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search
Chain-in-Tree cuts token use, model calls, and runtime by 75-85% in LLM tree search on GSM8K and Math500 by using simple branching-necessity checks, with little accuracy loss in most cases.
-
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
DeepSearch embeds MCTS into RLVR training with global frontier selection, entropy guidance, and adaptive replay to achieve 62.95% average accuracy on math reasoning benchmarks while using 5.7x fewer GPU hours than ext...
-
AdsQA: Towards Advertisement Video Understanding
AdsQA adds an ad-video question-answering benchmark and ReAd-R, a GRPO-trained model that beats 7B baselines but not larger closed models.
-
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Parallel-R1 uses SFT cold-start on easy math plus GRPO on hard math to instill parallel thinking in Qwen3-4B, reporting 8.4% average accuracy gains and a 42.9% AIME25 gain from a parallel-exploration scaffold.
-
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
Multi-turn RL with only unary 'try again' feedback improves multi-turn reasoning accuracy by up to 14% while preserving single-turn performance.
-
Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search
DITS replaces Q-value guidance in MCTS with influence scores for synthetic data synthesis in multi-agent LLM training, claiming better efficiency and performance on eight datasets.
-
Scientific discovery as meta-optimization: a combinatorial optimization case study
Introduces consensus objective aggregation for meta-optimization of scientific discovery and reports improved scaling and speedup for 3-SAT algorithm discovery using digital MemComputing machines.
-
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
A disagreement-based router that decides per math problem whether to accept, majority-vote, or rewrite improves accuracy by 3–7% with fewer samples than fixed test-time scaling methods.
-
Bilevel Optimization of Agent Skills via Monte Carlo Tree Search
Bilevel optimization with outer-loop MCTS for skill structure and inner-loop LLM refinement improves agent accuracy on an operations-research question-answering dataset.
-
Automatically Generating Hard Math Problems from Hypothesis-Driven Error Analysis
A hypothesis-driven pipeline generates targeted hard math problems that drop Llama-3.3-70B-Instruct accuracy from 77% on MATH to as low as 45%.
-
Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction
A multi-LoRA distillation method with knowledge generation, deep reasoning, and iterative consistency checking improves small-model math reasoning accuracy on GSM8K.
-
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
A jailbreak defense that reasons about hidden manipulations in attack prompts, trained with supervised fine-tuning plus entropy-guided reinforcement learning, generalizes to attacks never seen in training.
-
EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique
A multi-stage framework (data filtering, MCTS-guided trajectory construction, PRM-based reranking) improves Qwen MLLMs' accuracy on K-12 multimodal science benchmarks.
-
Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning
K-MSE adds a substructure knowledge base, a learned molecule-spectrum scorer, and Monte Carlo tree search, lifting LLM exact-match accuracy on MolPuzzle from 3.7% to 27.3% (GPT-4o-mini) and from 27.8% to 57.8% (GPT-4o).
-
Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding
A confidence-guided iterative zoom-in framework improves long-video question answering for multimodal LLMs without any training.
-
Efficient Graph Understanding with LLMs via Structured Context Injection
Giving LLMs graph inputs whose nodes are named after Game of Thrones characters, with relationship weights, raises accuracy on four graph-reasoning tasks using a single prompt.
-
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
A step-level verifier-guided hybrid of Best-of-N sampling, Monte Carlo tree search, and conditional self-refinement improves reasoning in small instruction-tuned LLMs, claiming up to 28.6-point gains.
-
Position: How can Graphs Help Large Language Models?
Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
Discussion (0). Sign in to comment.