Towards Inference-time Scaling for Continuous Space Reasoning

• URL: http://arxiv.org/abs/2510.12167v2
• Date: Fri, 17 Oct 2025 00:39:44 GMT
• Title: Towards Inference-time Scaling for Continuous Space Reasoning
• Authors: Minghan Wang, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari,
• Abstract summary: Inference-time scaling has proven effective for text-based reasoning in large language models.<n>This paper investigates whether such established techniques can be successfully adapted to reasoning in the continuous space.<n>We demonstrate the feasibility of generating diverse reasoning paths through dropout-based sampling.
• Score: 55.40260529506702
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inference-time scaling through multiple sample generation in combination with Process- or Outcome-Reward Model (PRM or ORM) re-ranking has proven effective for text-based reasoning in large language models. This paper investigates whether such established techniques can be successfully adapted to reasoning in the continuous space, using COCONUT (Hao et al. 2024) continuous space reasoning LM as the backbone. We demonstrate the feasibility of generating diverse reasoning paths through dropout-based sampling. Our Pass@N analysis on the generated samples reveals the potential that could enable a significant gain in performance akin to observed gain in the discrete space. However, we highlight unique challenges faced for materializing this gain in the continuous thought space. In particular, working recipes for data generation and training PRM and ORM models in the discrete space unlocks only marginal improvements in the continuous space. Through probing various aspects including geometric properties and trajectory dynamics we identify the underlying reasons that prevent effective discrimination between correct and incorrect reasoning (essential for the functioning of PRM and ORM). Our findings reveal that current limitations stem from the absence of key inductive biases in continuous thought representations. We argue that the training frameworks for continuous reasoning LMs require not only to optimize for accuracy but also to explicitly incorporate inductive biases that could be utilized during inference-time for discrimination of correct and incorrect thoughts.\footnote{Our code and data will be publicly available.}

Related papers

• GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler [54.10960908347221]
  We model latent thought exploration as conditional sampling from learnable densities and instantiate this idea as a Gaussian Thought Sampler (GTS)<n>GTS predicts context-dependent perturbation distributions over continuous reasoning states and is trained with GRPO-style policy optimization while keeping the backbone frozen.
  arXiv  Detail & Related papers  (2026-02-15T09:57:47Z)
• Reinforcement Learning for Latent-Space Thinking in LLMs [2.3431309298961644]
  Chain-of-Thought (CoT) reasoning typically utilizes the discrete language space for thinking.<n> latent-space thinking allows models to think using the continuous embedding space.
  arXiv  Detail & Related papers  (2025-11-26T21:43:24Z)
• SELF-REDRAFT: Eliciting Intrinsic Exploration-Exploitation Balance in Test-Time Scaling for Code Generation [12.241337921137259]
  Test-time scaling without interpreter feedback is essential for real-world code generation scenarios.<n>We introduce SELF-REDRAFT, a framework built upon Self-Refine that encourages the model to propose new drafts for solutions that are fundamentally flawed.
  arXiv  Detail & Related papers  (2025-10-31T06:30:47Z)
• Counterfactual Explanations in Medical Imaging: Exploring SPN-Guided Latent Space Manipulation [2.9810923705287524]
  In medical image analysis, deep learning models have demonstrated remarkable performance.<n>Deep generative models such as variational autoencoders (VAEs) exhibit significant generative power.<n>Probability models like sum-product networks (SPNs) efficiently represent complex joint probability distributions.
  arXiv  Detail & Related papers  (2025-07-25T15:19:32Z)
• A Survey on Latent Reasoning [100.54120559169735]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities.<n>CoT reasoning that verbalizes intermediate steps limits the model's expressive bandwidth.<n>Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state.
  arXiv  Detail & Related papers  (2025-07-08T17:29:07Z)
• Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models [86.88657425848547]
  Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning.<n>We explicitly align models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks.<n>Our three stage-pipeline individual alignment, parameter-space merging, and domain-specific reinforcement learning, boosts performance by over 10% relative to instruction-tuned baselines.
  arXiv  Detail & Related papers  (2025-05-15T17:58:33Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Spatial Reasoning with Denoising Models [49.83744014336816]
  We introduce a framework to perform reasoning over sets of continuous variables via denoising generative models.<n>For the first time, that order of generation can successfully be predicted by the denoising network itself.<n>Using these findings, we can increase the accuracy of specific reasoning tasks from 1% to >50%.
  arXiv  Detail & Related papers  (2025-02-28T14:08:30Z)
• Disentangled Interleaving Variational Encoding [1.132458063021286]
  We propose a principled approach to disentangle the original input into marginal and conditional probability distributions in the latent space of a variational autoencoder.<n>Our proposed model, Deep Disentangled Interleaving Variational.<n>coder (DeepDIVE), learns disentangled features from the original input to form clusters in the embedding space.<n>Experiments on two public datasets show that DeepDIVE disentangles the original input and yields forecast accuracies better than the original VAE.
  arXiv  Detail & Related papers  (2025-01-15T10:50:54Z)
• Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models [15.817239008727789]
  In this work, we analyze a specific type of causal query called domain counterfactuals, which hypothesizes what a sample would have looked like if it had been generated in a different domain. We show that recovering the latent Structural Causal Model (SCM) is unnecessary for estimating domain counterfactuals. We also develop a theoretically grounded practical algorithm that simplifies the modeling process to generative model estimation.
  arXiv  Detail & Related papers  (2023-06-20T04:19:06Z)
• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders [63.46738617561255]
  We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder. We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not. Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
  arXiv  Detail & Related papers  (2020-10-19T01:27:21Z)
• Modal Uncertainty Estimation via Discrete Latent Representation [4.246061945756033]
  We introduce a deep learning framework that learns the one-to-many mappings between the inputs and outputs, together with faithful uncertainty measures. Our framework demonstrates significantly more accurate uncertainty estimation than the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-25T05:29:34Z)

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.