GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time

• URL: http://arxiv.org/abs/2510.03777v1
• Date: Sat, 04 Oct 2025 11:02:39 GMT
• Title: GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
• Abstract summary: We propose a new inference algorithm, GuidedSampling, which decouples the exploration and generation phases during inference.<n>The exploration phase identifies multiple concepts that can be utilized to solve the problem, while the generation phase applies a specific concept to provide final solution candidates.
• Score: 40.94165318043027
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference time, it often struggles to generate diverse solution candidates, frequently relying on the same underlying approach to solve the problem and thus producing redundant samples. To address this limitation, we propose a new inference algorithm, GuidedSampling, which decouples the exploration and generation phases during inference, increasing diversity of generated candidate solutions. The exploration phase identifies multiple concepts that can be utilized to solve the problem, while the generation phase applies a specific concept to provide final solution candidates. We first define the theoretical bounds of GuidedSampling and then empirically demonstrate that it improves the performance of base model at pass@50 by on an average ~21.6% across various benchmarks compared to RS. Furthermore, models trained on trajectories of GuidedSampling exhibit substantial performance improvements at pass@5 by on an average ~9.7%, compared to models trained on traditional RS. Additionally, models trained with GuidedSampling increases the average number of concepts per instance (1.67 -> 3.03), yielding a diverse set of candidates than traditional RS.

Related papers

• Learning Early-to-Final Solution Consistency for MILP Acceleration [23.616127937763896]
  Mixed-Integer Linear Programming (MILP) is a fundamental problem class in operations research and optimization.<n>Recent learning-based approaches seek to accelerate MILP solving by directly predicting high-quality solutions from static instance-level features.<n>We propose a new solver-informed paradigm that shifts the learning target from variable assignment to early-to-final consistency.
  arXiv  Detail & Related papers  (2026-08-20T12:18:56Z)
• Optimizing Visual Generative Models via Distribution-wise Rewards [57.46109819595665]
  We present a novel framework that finetunes generative models using distribution-wise rewards, ensuring better alignment with real-world data distributions.<n>Our approach significantly improves FID-50K across various base models, from 5.77 for SiT and from 3.74 to 3.52 for EDM2.
  arXiv  Detail & Related papers  (2026-07-02T15:08:56Z)
• Reasoning with Sampling: Your Base Model is Smarter Than You Think [52.639108524651846]
  We propose a simple iterative sampling algorithm leveraging the base models' own likelihoods.<n>We show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL.<n>Our method does not require training, curated datasets, or a verifier.
  arXiv  Detail & Related papers  (2025-10-16T17:18:11Z)
• Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models [66.60042743462175]
  We present a copula-based approach to efficiently generate accurate, correlated sample paths from time series foundation models.<n>Our approach generates correlated sample paths orders of magnitude faster than autoregressive sampling.
  arXiv  Detail & Related papers  (2025-10-02T17:08:58Z)
• SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion [0.8594140167290097]
  SPREAD is a generative framework based on Denoising Diffusion Probabilistic Models (DDPMs)<n>It learns a conditional diffusion process over points sampled from the decision space.<n>It refines candidates via a sampling scheme that uses an adaptive multiple gradient descent-inspired update for fast convergence.
  arXiv  Detail & Related papers  (2025-09-25T12:09:37Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• Reinforce LLM Reasoning through Multi-Agent Reflection [8.088795955922656]
  We introduce DPSDP, a reinforcement learning algorithm that trains an actor-critic LLM system to iteratively refine answers via direct preference learning on self-generated data.<n>Theoretically, DPSDP can match the performance of any policy within the training distribution.<n>For example, on benchmark MATH 500, majority voting over five refinement steps increases first-turn accuracy from 58.2% to 63.2% with Ministral-based models.
  arXiv  Detail & Related papers  (2025-06-10T02:43:47Z)
• Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning [69.64809103333839]
  We investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning.<n>Our approach demonstrates significant performances across various multi-modal mathematical reasoning benchmarks with only 2K+0.6K two-stage training data.
  arXiv  Detail & Related papers  (2025-05-19T15:43:10Z)
• On the Effect of Sampling Diversity in Scaling LLM Inference [57.31028064284527]
  Large language model (LLM) scaling inference is key to unlocking greater performance.<n>Motivated by the observed relationship between solution accuracy and meaningful response diversity, we systematically study the effect of prompt diversity in scaling inference.<n>We show that responses generated from meaningful diverse prompts after Best-of-$N$ selection exhibit significantly lower error rates than those produced from stationary prompts.
  arXiv  Detail & Related papers  (2025-02-16T07:37:58Z)
• Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs [3.6696973040141034]
  path-consistency improves inference latency by up to 40.5%, while maintaining task accuracy across various tasks.<n>Our empirical results demonstrate that path-consistency improves inference latency by up to 40.5%, while maintaining task accuracy across various tasks.
  arXiv  Detail & Related papers  (2024-08-25T01:45:53Z)
• Sampling Through the Lens of Sequential Decision Making [9.101505546901999]
  We propose a reward-guided sampling strategy called Adaptive Sample with Reward (ASR) Our approach optimally adjusts the sampling process to achieve optimal performance. Empirical results in information retrieval and clustering demonstrate ASR's superb performance across different datasets.
  arXiv  Detail & Related papers  (2022-08-17T04:01:29Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Squared $\ell_2$ Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations [76.85274970052762]
  Regularizing distance between embeddings/representations of original samples and augmented counterparts is a popular technique for improving robustness of neural networks. In this paper, we explore these various regularization choices, seeking to provide a general understanding of how we should regularize the embeddings. We show that the generic approach we identified (squared $ell$ regularized augmentation) outperforms several recent methods, which are each specially designed for one task.
  arXiv  Detail & Related papers  (2020-11-25T22:40:09Z)

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.