SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation

• URL: http://arxiv.org/abs/2506.06470v1
• Date: Fri, 06 Jun 2025 18:55:16 GMT
• Title: SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
• Abstract summary: Monte Carlo Tree Search is a powerful technique for generating high-quality chain-of-thought data.<n> conventional approaches typically retain only the top-scoring trajectory from the search tree.<n>We propose SIGMA, a novel framework that reintegrates these discarded sibling nodes to refine LLM reasoning.
• Score: 38.37231157929935
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Enhancing large language models by simply scaling up datasets has begun to yield diminishing returns, shifting the spotlight to data quality. Monte Carlo Tree Search (MCTS) has emerged as a powerful technique for generating high-quality chain-of-thought data, yet conventional approaches typically retain only the top-scoring trajectory from the search tree, discarding sibling nodes that often contain valuable partial insights, recurrent error patterns, and alternative reasoning strategies. This unconditional rejection of non-optimal reasoning branches may waste vast amounts of informative data in the whole search tree. We propose SIGMA (Sibling Guided Monte Carlo Augmentation), a novel framework that reintegrates these discarded sibling nodes to refine LLM reasoning. SIGMA forges semantic links among sibling nodes along each search path and applies a two-stage refinement: a critique model identifies overlooked strengths and weaknesses across the sibling set, and a revision model conducts text-based backpropagation to refine the top-scoring trajectory in light of this comparative feedback. By recovering and amplifying the underutilized but valuable signals from non-optimal reasoning branches, SIGMA substantially improves reasoning trajectories. On the challenging MATH benchmark, our SIGMA-tuned 7B model achieves 54.92% accuracy using only 30K samples, outperforming state-of-the-art models trained on 590K samples. This result highlights that our sibling-guided optimization not only significantly reduces data usage but also significantly boosts LLM reasoning.

Related papers

• StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling [13.71352763893512]
  We propose StarOR, a search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling.<n>StarOR decomposes the modeling process into four stages and updates a transient LoRA adapter via GRPO at each non-terminal node.<n> Experiments across five optimization benchmarks show that StarOR achieves state-of-the-art performance even with a 4B backbone.
  arXiv  Detail & Related papers  (2026-06-13T08:46:13Z)
• Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories [26.441136942925056]
  Contrastive Reasoning Path Synthesis (CRPS) is a framework that transforms supervision extraction into a synthesis procedure.<n>CRPS uses a structured reflective process to analyze the differences between high- and low-quality search trajectories, extracting explicit information about strategic pivots and local failure modes.<n>We show empirically that models fine-tuned on just 60K CRPS-synthesized examples match or exceed the performance of baselines trained on 590K examples derived from standard rejection sampling.
  arXiv  Detail & Related papers  (2026-04-13T12:05:34Z)
• Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation [16.991391135071513]
  We propose V-STAR, a Value-guided Sampling and Tree-structured Advantage Reinforcement framework.<n>V-STAR forms a self-evolving loop via two synergistic components. First, a Value-Guided Efficient Decoding (VED) is developed to identify decisive nodes and selectively deepen high-potential prefixes.<n>Second, we propose Sibling-GRPO, which exploits the induced tree topology to compute sibling-relative advantages and concentrates learning signals on decisive branching decisions.
  arXiv  Detail & Related papers  (2026-02-11T09:57:36Z)
• SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models [53.19726629537694]
  Post-training alignment of video generation models with human preferences is a critical goal.<n>Current data collection paradigms, reliant on in-prompt pairwise annotations, suffer from labeling noise.<n>We propose SoliReward, a systematic framework for video RM training.
  arXiv  Detail & Related papers  (2025-12-17T14:28:23Z)
• Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling [90.87033586963828]
  Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs)<n>We propose Self-Consistency Sampling (SCS) to correct this issue.<n>Based on Qwen2.5-VL-7B-Instruct, SCS improves accuracy by up to 7.7 percentage points on six multimodal benchmarks with negligible extra computation.
  arXiv  Detail & Related papers  (2025-11-13T18:59:57Z)
• Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS [19.394761422323853]
  We introduce R2-LLMs, a novel and versatile hierarchical retrieval-augmented reasoning framework.<n>R2-LLMs enhances inference-time generalization by integrating dual-level retrieval-based in-context learning.<n> Empirical evaluations on the MATH500, GSM8K, and OlympiadBench-TO datasets achieve substantial relative improvement.
  arXiv  Detail & Related papers  (2025-07-08T00:41:12Z)
• RETENTION: Resource-Efficient Tree-Based Ensemble Model Acceleration with Content-Addressable Memory [9.502789435634975]
  RETENTION is an end-to-end framework that significantly reduces CAM capacity requirement for tree-based model inference.<n>We present a tree mapping scheme that incorporates two innovative data placement strategies to alleviate the memory redundancy caused by the widespread use of don't care states in CAM.
  arXiv  Detail & Related papers  (2025-06-06T11:25:51Z)
• Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst [42.40884882220895]
  We introduce textitSelf-Reasoning Language Model (SRLM), where the model itself can synthesize longer CoT data and improve performance through self-training.<n>Our proposed SRLM achieves an average absolute improvement of more than $+2.5$ points across five reasoning tasks.
  arXiv  Detail & Related papers  (2025-05-20T09:21:26Z)
• Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models [39.22557129190619]
  Distillation--post-training on LRMs-generated data--is a straightforward yet effective method to enhance the reasoning abilities of smaller models.<n>To alleviate this bottleneck, we propose constructing tree-based CoT data from scratch via Monte Carlo Tree Search.<n>We then exploit a set of CoT-aware approaches, including Thoughts Length Balance, Fine-grained DPO, and Joint Post-training Objective, to enhance SFT and RL on the constructed data.
  arXiv  Detail & Related papers  (2025-03-03T12:17:36Z)
• I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search [10.718560472954644]
  Introspective Monte Carlo Tree Search (I-MCTS) is a novel approach that iteratively expands tree nodes through an introspective process.<n>We integrate a Large Language Model (LLM)-based value model to facilitate direct evaluation of each node's solution.<n>Our approach demonstrates a 6% absolute improvement in performance compared to the strong open-source AutoML agents.
  arXiv  Detail & Related papers  (2025-02-20T16:19:09Z)
• Chain-of-Retrieval Augmented Generation [72.06205327186069]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models [88.29990536278167]
  We introduce SPaR, a self-play framework integrating tree-search self-refinement to yield valid and comparable preference pairs.<n>Our experiments show that a LLaMA3-8B model, trained over three iterations guided by SPaR, surpasses GPT-4-Turbo on the IFEval benchmark without losing general capabilities.
  arXiv  Detail & Related papers  (2024-12-16T09:47:43Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)
• Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents [9.191944519634111]
  The Georgetown InfoSense group has done in regard to solving the challenges presented by TREC iKAT 2023. Our submitted runs outperform the median runs by a significant margin, exhibiting superior performance in nDCG across various cut numbers and in overall success rate. Our solution involves the use of Large Language Models (LLMs) for initial answers, answer grounding by BM25, passage quality filtering by logistic regression, and answer generation by LLMs again.
  arXiv  Detail & Related papers  (2023-11-16T02:37:58Z)
• AffineGlue: Joint Matching and Robust Estimation [74.04609046690913]
  We propose AffineGlue, a method for joint two-view feature matching and robust estimation. AffineGlue selects potential matches from one-to-many correspondences to estimate minimal models. Guided matching is then used to find matches consistent with the model, suffering less from the ambiguities of one-to-one matches.
  arXiv  Detail & Related papers  (2023-07-28T08:05:36Z)
• Lookback for Learning to Branch [77.32867454769936]
  Bipartite Graph Neural Networks (GNNs) have been shown to be an important component of deep learning based Mixed-Integer Linear Program (MILP) solvers. Recent works have demonstrated the effectiveness of such GNNs in replacing the branching (variable selection) in branch-and-bound (B&B) solvers.
  arXiv  Detail & Related papers  (2022-06-30T02:33:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.