REVIEW 18 cited by
Interpretable Contrastive Monte Carlo Tree Search Reasoning
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
We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works often overlooked its biggest drawback--slower speed compared to CoT; 2. Previous research mainly used MCTS as a tool for LLM reasoning on various tasks with limited quantitative analysis or ablation studies of its components from reasoning interpretability perspective. 3. The reward model is the most crucial component in MCTS, however previous work has rarely conducted in-depth study or improvement of MCTS's reward models. Thus, we conducted extensive ablation studies and quantitative analysis on components of MCTS, revealing the impact of each component on the MCTS reasoning performance of LLMs. Building on this, (i) we designed a highly interpretable reward model based on the principle of contrastive decoding and (ii) achieved an average speed improvement of 51.9% per node using speculative decoding. Additionally, (iii) we improved UCT node selection strategy and backpropagation used in previous works, resulting in significant performance improvement. We outperformed o1-mini by an average of 17.4% on the Blocksworld multi-step reasoning dataset using Llama-3.1-70B with SC-MCTS*. Our code is available at https://github.com/zitian-gao/SC-MCTS.
Forward citations
Cited by 18 Pith papers
-
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.
-
Procedural Knowledge at Scale Improves Reasoning
Retrieving compact procedural hints from 32M subquestion–subroutine pairs improves reasoning-model accuracy on math, science, and coding benchmarks beyond compute-matched test-time scaling.
-
NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
NeuroSymActive combines soft-unification symbolic modules, a neural path evaluator, and Monte-Carlo-style active exploration to reach strong answer accuracy on KGQA benchmarks while cutting graph lookups and model cal...
-
LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model
RL training on preference-labeled critic data transforms a 7B vision-language model into both a stronger critic and a stronger generative policy, improving average benchmark accuracy by 5.7% and enabling self-critique...
-
Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need
A language model fine-tuned on knowledge-graph-path reasoning tasks (QwQ-Med-3) beats strong baselines on a same-style benchmark but shows mixed gains on external medical QA tests.
-
Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements
MCTS enhancements such as MAST, NST, GRAVE, Score Bounded MCTS, and PN-MCTS can provide extra, knowledge-free data for explaining MCTS decisions, illustrated with examples in the Ludii system.
-
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.
-
Growing Through Experience: Scaling Episodic Grounding in Language Models
A weak-to-strong training pipeline using MCTS-collected experiences and behavior-ratio distillation improves large LM planning on VirtualHome, with a 405B inference-time variant scoring 74.34 versus GPT-4o's 70.89.
-
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
A stochastic scheduling framework that modulates slow-to-fast reasoning in large reasoning models at test time, improving accuracy while reducing token usage.
-
Hume: Introducing System-2 Thinking in Visual-Language-Action Model
A dual-system vision-language-action model that improves robot control by ranking multiple sampled action chunks with a learned value function before fast execution.
-
Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions
Influence-function attribution shows high-difficulty math and low-difficulty code training data best improve math and code reasoning, and difficulty-based reweighting improves benchmark performance.
-
MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning
MARCO combines cross-problem knowledge accumulation with cross-agent lesson sharing to improve LLM code reasoning at inference time.
-
Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models
Monte Carlo tree search can pick better slot-filling orders for masked diffusion language models, but the claimed advantage over autoregressive models depends on truncating the autoregressive baselines.
-
Joint Enhancement of Relational Reasoning for Long-Context LLMs
JERR builds a directed graph of summarized text chunks and uses Monte Carlo Tree Search to retrieve relevant nodes, reportedly improving long-context QA over baselines.
-
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.
-
Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories
Large reasoning models frequently ignore explicitly injected ground-truth solutions mid-trajectory and continue to overthink, often ending on incorrect answers.
-
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
Autonomous AI becomes dependable when tool use is embedded in persistent workspaces with reusable skills, shifting evaluation from answers to task closure.
Discussion (0). Sign in to comment.