REVIEW 19 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
Interpretable Contrastive Monte Carlo Tree Search Reasoning
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 19 Pith papers
-
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.
-
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Cross-modal agreement between chain-of-thought and program-of-thought reasoning enables self-consistency with only two LLM samples, reducing sampling cost by 9.3x while improving accuracy.
-
Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies
DPTS shows cold-start bottlenecks at low budgets while SSDP exhibits frontier depletion, indicating fixed ToT strategies are inelastic across compute levels.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX accelerates Tree-of-Thought LLM reasoning 1.2-3x via speculative path selection, dynamic budget allocation across queries, and adaptive early termination, with up to 4.1x when combined with token speculative decoding.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX delivers 1.2-3x speedup on ToT algorithms via speculative path selection, dynamic budget allocation, and adaptive early termination, reaching up to 4.1x when combined with token-level speculative decoding.
-
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.
-
M2-PALE: A Framework for Explaining Multi-Agent MCTS--Minimax Hybrids via Process Mining and LLMs
M2-PALE extracts process models from multi-agent MCTS-Minimax execution traces using Alpha Miner, iDHM and Inductive Miner, then uses LLMs to generate causal explanations, shown in a small checkers setting.
-
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.
-
Procedural Knowledge at Scale Improves Reasoning
Reasoning Memory decomposes reasoning trajectories into 32 million subquestion-subroutine pairs and retrieves them via in-thought prompts to improve language model performance on math, science, and coding benchmarks b...
-
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...
-
Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
Curtailing diversity in candidate pools for test-time scaling increases unsafe LLM outputs, as demonstrated by a reference-guided reduction protocol that evades standard safety classifiers across open and closed models.
-
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...
-
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.
-
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.
-
Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
PODS applies max-variance down-sampling to GRPO rollouts in LLM RLVR, delivering at least 1.7x faster training to peak test accuracy on reasoning benchmarks.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
-
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.
-
NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
NeuroSymActive claims state-of-the-art KGQA accuracy (WebQSP 87.1, CWQ 62.5 Hits@1) by coupling differentiable neural-symbolic reasoning with uncertainty-guided MCTS and active human queries.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.