Reasoning with Sampling: Your Base Model is Smarter Than You Think

• URL: http://arxiv.org/abs/2510.14901v1
• Date: Thu, 16 Oct 2025 17:18:11 GMT
• Title: Reasoning with Sampling: Your Base Model is Smarter Than You Think
• Authors: Aayush Karan, Yilun Du,
• Abstract summary: 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.
• Score: 52.639108524651846
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilites can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models' own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains.

Related papers

• You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models [12.14455026524814]
  We investigate the generalizability of label-free RL approaches to base models with limited reasoning capabilities.<n>We find that label-free RL is highly dependent on the base model's pre-existing reasoning capability.<n>We propose a simple yet effective method for label-free RL that utilizes curriculum learning to progressively introduce harder problems.
  arXiv  Detail & Related papers  (2025-11-07T01:05:11Z)
• Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions [22.83151273022573]
  counterintuitive phenomena have been reported in large language models (LLMs)<n>We identify a key factor that differentiates RL observations: whether the pretrained model already exhibits strong Model-Task Alignment.<n>Our findings show that while standard RL training remains consistently robust across settings, many of these counterintuitive results arise only when the model and task already exhibit strong model-task alignment.
  arXiv  Detail & Related papers  (2025-08-28T20:02:10Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning [12.83211408922535]
  Reinforcement learning-style post-training improves reasoning by optimizing model outputs based on reward or preference signals.<n> GRPO-style approaches implement this by using self-generated samples labeled by an outcome-based verifier.<n>We propose $textbfSelf-Explanation Policy Optimization (ExPO)$-a simple and modular framework that generates such samples by conditioning on the ground-truth answer.
  arXiv  Detail & Related papers  (2025-07-03T17:44:55Z)
• ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models [89.37819814048288]
  We introduce ProRL, a novel training methodology that incorporates KL divergence control, reference policy, and a diverse suite of tasks.<n>Our empirical analysis reveals that RL-trained models consistently outperform base resetting models across a wide range of pass@k evaluations.<n>These findings offer new insights into the conditions under which RL meaningfully expands reasoning boundaries in language models.
  arXiv  Detail & Related papers  (2025-05-30T17:59:01Z)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models.<n>We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization [23.972397132797116]
  Current deep learning approaches rely on generative models that yield exact sample likelihoods.<n>This work introduces a method that lifts this restriction and opens the possibility to employ highly expressive latent variable models.<n>We experimentally validate our approach in data-free Combinatorial Optimization and demonstrate that our method achieves a new state-of-the-art on a wide range of benchmark problems.
  arXiv  Detail & Related papers  (2024-06-03T17:55:02Z)
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
  We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation. We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
  arXiv  Detail & Related papers  (2024-02-08T14:54:47Z)
• 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)
• PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration [15.173628100049129]
  This work studies a model-based algorithm for both Kernelized Regulators (KNR) and linear Markov Decision Processes (MDPs) For both models, our algorithm guarantees sample complexity and only uses access to a planning oracle. Our method can also perform reward-free exploration efficiently.
  arXiv  Detail & Related papers  (2021-07-15T15:49:30Z)

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.