When Does Latent Reasoning Help? MeRa: Metric-Space Bias for Spatial Prediction

• URL: http://arxiv.org/abs/2606.03727v1
• Date: Tue, 02 Jun 2026 14:47:30 GMT
• Title: When Does Latent Reasoning Help? MeRa: Metric-Space Bias for Spatial Prediction
• Abstract summary: We find that latent reasoning degrades spatial prediction below the unmodified baseline.<n>We formalize this finding through MeRa (Metric-space Reasoning), a lightweight backbone-agnostic module.<n>We prove that metric-space-constrained reasoning converges to a unique fixed point and that N-step reasoning is strictly more expressive than (N-1)-step reasoning.
• Score: 23.627157851520845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Latent reasoning has improved sequential recommendation by iteratively refining representations before prediction, but does it help spatial prediction? We find that the answer depends on whether reasoning is grounded in the underlying metric space. Without such grounding, latent reasoning degrades spatial prediction below the unmodified baseline, while a learned metric-space bias derived from pairwise distances produces consistent gains. We formalize this finding through MeRa (Metric-space Reasoning), a lightweight backbone-agnostic module that can be inserted between any sequence encoder and its prediction heads. On the GETNext backbone, the gap between reasoning without and with metric-space bias reaches 4.5% NDCG@10. MeRa achieves the best NDCG@10 on all three spatial prediction benchmarks among the compared methods, surpassing recent approaches such as GeoMamba and HMST. We prove that metric-space-constrained reasoning converges to a unique fixed point and that N-step reasoning is strictly more expressive than (N-1)-step reasoning. A controlled experiment on CLEVR with Euclidean distance confirms that the finding generalizes beyond geographic coordinates. The code is included in the supplementary material.

Related papers

• Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning [3.216436532980238]
  Chain-of-thought (CoT) reasoning improves the reasoning ability of large language models by introducing intermediate computation.<n>However, explicit rationales increase decoding length, latency, and context cost.<n>Implicit CoT offers a more efficient alternative by moving intermediate reasoning into continuous latent states.
  arXiv  Detail & Related papers  (2026-09-07T12:18:51Z)
• RecRec: Latent Interests Recursive Reasoning for Sequential Recommendation [52.23179023639867]
  Sequential recommender systems rely on a single forward pass to encode user interaction and predict the next item.<n>How to structure the reasoning process for sequential recommendation remains an open question.<n>Existing approaches couple reasoning and prediction in a single $d$-dimensional state, limiting reasoning depth.<n>We propose RecRec (Recursive Reasoning for Recommendation), an RL-free framework that overcomes fixed $d$-dimensional state of methods.
  arXiv  Detail & Related papers  (2026-07-14T16:28:28Z)
• Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model [47.71489969727656]
  Conformalized Quantile Regression (CQR) delivers the best coverage in the bin with the poorest model predictions.<n>Only the Locally Valid and Discriminative (LVD) framework provides finite-sample emphlocal validity.
  arXiv  Detail & Related papers  (2026-06-05T18:29:19Z)
• Geometric Latent Reasoning Induces Shorter Generations in LLMs [24.29594681334716]
  We formulate latent reasoning as a geometric path-approximation problem within the model's pretrained token-embedding space.<n>We introduce Geometric Latent Reasoning (GLR), which uses a lightweight transition head to predict iterative direction updates in embedding space.<n> Evaluations on mathematical reasoning benchmarks using Qwen3 models reveal an emergent phenomenon: geometric latent reasoning induces substantially shorter generations without an explicit length objective.
  arXiv  Detail & Related papers  (2026-06-01T13:40:55Z)
• Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA [50.494504099850325]
  We introduce the Geodesic Hypothesis, positing that token sequences trace geodesics on a smooth semantic manifold and are therefore locally linear.<n>We show this constraint improves signal-to-noise ratio, and preserves diversity by preventing collisions during trajectory.<n>We demonstrate that geometric priors can surpass brute-force scaling.
  arXiv  Detail & Related papers  (2026-02-26T04:45:07Z)
• Towards Inference-time Scaling for Continuous Space Reasoning [55.40260529506702]
  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.
  arXiv  Detail & Related papers  (2025-10-14T05:53:41Z)
• Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation [52.73824786627612]
  This paper establishes new convergence results for textitgeodesic strongly monotone games.<n>Our key result shows that RGD attains last-iterate linear convergence in a textitgeometry-agnostic fashion.<n>Overall, this paper presents the first geometry-agnostic last-iterate convergence analysis for games beyond the Euclidean settings.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• LMR: Lane Distance-Based Metric for Trajectory Prediction [10.83642398981694]
  Currently established metrics are based on Euclidean distance, which means that errors are weighted equally in all directions. We propose a new metric that is lane distance-based: Lane Miss Rate (LMR) LMR is defined as the ratio of sequences that yield a miss.
  arXiv  Detail & Related papers  (2023-04-12T13:59:04Z)
• Identifying latent distances with Finslerian geometry [6.0188611984807245]
  Generative models cause the data space and the geodesics to be at best impractical, and at worst impossible to manipulate. In this work, we propose another metric whose geodesics explicitly minimise the expected length of the pullback metric. In high dimensions, we prove that both metrics converge to each other at a rate of $Oleft(frac1Dright)$.
  arXiv  Detail & Related papers  (2022-12-20T05:57:27Z)
• Lassoed Tree Boosting [53.56229983630983]
  We prove that a gradient boosted tree algorithm with early stopping faster than $n-1/4$ L2 convergence in the large nonparametric space of cadlag functions of bounded sectional variation. Our convergence proofs are based on a novel, general theorem on early stopping with empirical loss minimizers of nested Donsker classes.
  arXiv  Detail & Related papers  (2022-05-22T00:34:41Z)
• Instance-Optimal Compressed Sensing via Posterior Sampling [101.43899352984774]
  We show for Gaussian measurements and emphany prior distribution on the signal, that the posterior sampling estimator achieves near-optimal recovery guarantees. We implement the posterior sampling estimator for deep generative priors using Langevin dynamics, and empirically find that it produces accurate estimates with more diversity than MAP.
  arXiv  Detail & Related papers  (2021-06-21T22:51:56Z)
• DeepKriging: Spatially Dependent Deep Neural Networks for Spatial Prediction [2.219504240642369]
  In spatial statistics, a common objective is to predict values of a spatial process at unobserved locations by exploiting spatial dependence. DeepKriging method has a direct link to Kriging in the Gaussian case, and it has multiple advantages over Kriging for non-Gaussian and non-stationary data. We apply the method to predicting PM2.5 concentrations across the continental United States.
  arXiv  Detail & Related papers  (2020-07-23T12:38:53Z)

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.