REVIEW 23 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 23 Pith papers
-
Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning
A checkpoint-based search and candidate augmentation method improves small LLM mathematical reasoning accuracy over existing test-time scaling baselines.
-
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...
-
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.
-
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.
-
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.
-
Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search
AutoCaption uses MCTS to generate fine-grained video key points, forming the MCTS-VCB benchmark that ranks MLLMs and yields training data improving a fine-tuned model's captioning.
-
SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-Refine
An LLM-based system combining specification analysis, waveform analysis, and Monte Carlo Tree Self-Refine generates SystemVerilog assertions that outperform AssertLLM and ChIRAAG on I2C and RV-Timer designs.
-
LLM-First Search: Self-Guided Exploration of the Solution Space
LLM-First Search, where the model itself decides whether to continue or backtrack during reasoning, outperforms MCTS, BestFS, and ToT-BFS on harder Countdown and Sudoku tasks while using fewer tokens.
-
ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search
A reward-guided tree search over a frozen protein language model designs diverse sequences that score higher on ESMFold-based self-consistency benchmarks than existing inverse folding methods.
-
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.
-
Detecting Voice Phishing with Precision: Fine-Tuning Small Language Models
Fine-tuning Llama-3-8B with human-authored voice phishing criteria outperforms chain-of-thought prompting and approaches GPT-4-level accuracy on a new adversarial Korean voice phishing benchmark.
-
Reward Model Generalization for Compute-Aware Test-Time Reasoning
The paper claims PRM generalization error controls test-time compute efficiency and that the proposed CATS controller improves accuracy on MATH-500 and AIME24.
-
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.
-
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning
A reward model that multiplies stepwise correctness and potential scores improves best-of-N verification accuracy for math reasoning.
-
SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition
A self-evaluating MCTS variant with semantic clustering gives small, statistically untested accuracy gains over CoT on MMLU subsets and Seal-Tools.
-
Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations
PDES orchestration of small language models with non-AI verifier agents raises accuracy on four toy tasks from about 23 percent to 68 percent, with the verifiers supplying most of the correctness.
Discussion (0). Sign in to comment.