LatentGeo: Learnable Auxiliary Constructions in Latent Space for Multimodal Geometric Reasoning

• URL: http://arxiv.org/abs/2603.12166v1
• Date: Thu, 12 Mar 2026 17:01:23 GMT
• Title: LatentGeo: Learnable Auxiliary Constructions in Latent Space for Multimodal Geometric Reasoning
• Abstract summary: We propose a framework that learns continuous latent visual representations to internalize auxiliary geometric constructions without pixel-level rendering or external executors.<n>LatentGeo achieves substantial gains on geometric reasoning tasks, particularly those requiring auxiliary constructions.
• Score: 32.39048489202347
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent advances in multimodal reasoning, representing auxiliary geometric constructions remains a fundamental challenge for multimodal large language models (MLLMs). Such constructions are absent from the original diagram and must be introduced before theorems apply. Existing approaches predominantly rely on explicit construction paradigms, including text-based geometric specification, visual-token interleaving during reasoning, and tool-augmented geometric execution. However, these methods either fail to faithfully represent complex spatial relationships, incur representation mismatch between discrete symbols and continuous geometric structures, or rely on external capabilities that hinder end-to-end optimization. To address these limitations, we propose LatentGeo, a framework that learns continuous latent visual representations to internalize auxiliary geometric constructions without pixel-level rendering or external executors. We design a three-stage curriculum that progressively aligns and internalizes these latent representations through auxiliary visual supervision, followed by LaGDPO, a latent-aware reinforcement learning procedure that stabilizes latent representations during policy optimization while improving end-task correctness. To systematically evaluate construction-centric representation quality, we introduce GeoAux, a new benchmark targeting visually dependent geometry problems, and conduct experiments on GeoAux and MathVerse. Results show that LatentGeo achieves substantial gains on geometric reasoning tasks, particularly those requiring auxiliary constructions. Extensive analyses and ablation studies further validate the effectiveness of each component in our framework.

Related papers

• Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal Language [60.70116693224378]
  We design a unified formal language that integrates plane and solid geometry, comprehensively covering geometric structures and semantic relations.<n>We construct GDP-29K, a large-scale dataset comprising 20k plane and 9k solid geometry samples collected from diverse real-world sources.
  arXiv  Detail & Related papers  (2026-04-13T15:09:56Z)
• Make Geometry Matter for Spatial Reasoning [62.61667611352403]
  Vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited.<n>Recent advances try to handle this limitation by injecting geometry tokens from pretrained 3D foundation models into VLMs.<n>We propose GeoSR, a framework designed to make geometry matter by encouraging VLMs to actively reason with geometry tokens.
  arXiv  Detail & Related papers  (2026-03-27T17:45:12Z)
• Thinking with Constructions: A Benchmark and Policy Optimization for Visual-Text Interleaved Geometric Reasoning [45.18040184559187]
  We present a framework for Visual-Text Interleaved Chain-of-Thought.<n>We first introduce GeoAux-Bench, the first benchmark comprising 4,334 geometry problems that align textual construction steps with ground-truth visual updates.<n>Our pilot study reveals two critical insights: (1) interleaved visual-textual aids outperform single-modality counterparts, which cannot losslessly capture geometric synergy; and (2) valid constructions act as entropy reducers, strongly correlating with reduced reasoning perplexity.
  arXiv  Detail & Related papers  (2026-03-19T09:27:20Z)
• GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning [51.63457948949102]
  We develop a framework to overcome the limited spatial understanding of Multimodal Large Language Models (MLLMs)<n>Our framework endows the model with an awareness of perceptual insufficiency, empowering it to autonomously engage geometric features in reasoning when 2D cues are deemed insufficient.
  arXiv  Detail & Related papers  (2026-03-11T03:32:12Z)
• Thinking with Geometry: Active Geometry Integration for Spatial Reasoning [68.59084007360615]
  We propose GeoThinker, a framework that shifts paradigm passive fusion to active perception.<n>Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands.<n>Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence.
  arXiv  Detail & Related papers  (2026-02-05T18:59:32Z)
• GeoSketch: A Neural-Symbolic Approach to Geometric Multimodal Reasoning with Auxiliary Line Construction and Affine Transformation [28.500787311066563]
  GeoSketch is a neural-symbolic framework that recasts geometric reasoning as an interactive perception-reasoning-action loop.<n>By unifying hierarchical decision-making, executable visual actions, and symbolic verification, GeoSketch advances multimodal reasoning from static interpretation to dynamic interaction.
  arXiv  Detail & Related papers  (2025-09-26T15:12:04Z)
• GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutions [45.70578816057097]
  We introduce the task of Referring Expression (REC) for geometric problems.<n>REC evaluates whether models can localize points, shapes, and spatial relations in diagrams in response to textual prompts.<n>We generate a large-scale synthetic training dataset using a structured geometric formal language.
  arXiv  Detail & Related papers  (2025-09-25T12:00:52Z)
• GeometryZero: Improving Geometry Solving for LLM with Group Contrastive Policy Optimization [63.107398132743825]
  Group Contrastive Policy Optimization (GCPO) is a novel reinforcement learning framework featuring two key innovations.<n>We develop GeometryZero, a family of affordable-size geometric reasoning models that judiciously determine when to employ auxiliary construction.
  arXiv  Detail & Related papers  (2025-06-08T14:18:15Z)
• GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training [45.42400674977197]
  GeoX is a multi-modal large model focusing on geometric understanding and reasoning tasks.<n>We introduce unimodal pre-training to develop a diagram encoder and symbol decoder, enhancing the understanding of geometric images and corpora.<n>We propose a Generator-And-Sampler Transformer (GS-Former) to generate discriminative queries and eliminate uninformative representations from unevenly distributed geometric signals.
  arXiv  Detail & Related papers  (2024-12-16T15:20:03Z)
• Geometric Deep Learning for Structure-Based Drug Design: A Survey [83.87489798671155]
  Structure-based drug design (SBDD) leverages the three-dimensional geometry of proteins to identify potential drug candidates. Recent advancements in geometric deep learning, which effectively integrate and process 3D geometric data, have significantly propelled the field forward.
  arXiv  Detail & Related papers  (2023-06-20T14:21:58Z)
• Representing Deep Neural Networks Latent Space Geometries with Graphs [38.63434325489782]
  Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems.
  arXiv  Detail & Related papers  (2020-11-14T17:21:29Z)

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.