MindTopo: Can Foundation Models Reason in Topological Space?

• URL: http://arxiv.org/abs/2609.11900v1
• Date: Thu, 10 Sep 2026 17:54:32 GMT
• Title: MindTopo: Can Foundation Models Reason in Topological Space?
• Abstract summary: We introduce MindTopo, a benchmark of topological intuition across five properties grounded in cognitive science and formal topology.<n>MindTopo evaluates each property at two cognitive levels. Reasoning asks a model to identify topological relations or infer how they change.<n>Every MLLM performs better on reasoning than on planning, and the best-performing model remains far below observed human performance.
• Score: 52.56750995613252
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these relations as foundational to spatial understanding, yet foundation-model evaluations largely focus on metric or viewpoint-dependent relations. We introduce MindTopo, a benchmark of topological intuition across five properties grounded in cognitive science and formal topology: continuity, separation, order, enclosure, and knots. MindTopo evaluates each property at two cognitive levels. Reasoning asks a model to identify topological relations or infer how they change. Planning instantiates a foundation model as a closed-loop agent whose policy selects environment actions. MindTopo contains 11,030 instances across 13 procedurally generated task types with controllable difficulty. We benchmark 14 MLLMs and study agent configurations augmented with image and video generation, including 3 video generative models in planning settings. Every MLLM performs better on reasoning than on planning, and the best-performing model remains far below observed human performance. On Qwen3-VL-2B-Instruct, supervised fine-tuning and reinforcement learning improve reasoning more than planning. Generated observations retain local cues and reach plausible endpoints, but audited rollouts do not reliably follow environment dynamics or preserve topology across transitions. Our website is at https://mind-topo.github.io/

Related papers

• Nested Episodic State Topology (NEST): A Graph-Theoretic Architecture of Cognitive States [0.0]
  NEST is a graph-theoretic representational ontology for modeling cognition.<n> Concepts, episodes, percepts, and task contexts are represented as typed, weighted graphs.<n>A reusable operator toolkit organizes the formal core.
  arXiv  Detail & Related papers  (2026-07-07T09:31:55Z)
• Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency [53.28076739140119]
  We propose a framework that enforces logical consistency in Vision-Language Models (VLMs) through geometric and linguistic duality operations.<n>SAGE is model-agnostic, data-efficient compared to prior GRPO methods, and can be applied as a lightweight post-training stage to any existing VLM.<n> Experiments on video and spatial reasoning benchmarks demonstrate consistent improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-05-18T10:05:21Z)
• No Triangulation Without Representation: Generalization in Topological Deep Learning [21.366284585034474]
  We show that both graph neural networks (GNNs) and higher-order message passing (HOMP) methods can saturate the benchmark.<n>Surprisingly, we find no indication that existing models are capable of generalizing beyond the structure of the data.
  arXiv  Detail & Related papers  (2026-05-07T15:55:24Z)
• SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments [75.60795462502949]
  SpatialEvo is a self-evolving framework for 3D spatial reasoning.<n>It formalizes 16 spatial reasoning task categories under explicit geometric validation rules.<n>It converts unannotated 3D scenes into zero-noise interactive oracles, replacing model consensus with objective physical feedback.
  arXiv  Detail & Related papers  (2026-04-15T17:59:12Z)
• World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models [25.135316296678187]
  Existing methods either overfit statistical shortcuts via 3D grounding data or remain confined to 2D visual perception.<n>We propose World2Mind, a training-free spatial intelligence toolkit.<n>We show that World2Mind boosts the performance of frontier models, such as GPT-5.2, by 5%18%.
  arXiv  Detail & Related papers  (2026-03-10T15:12:14Z)
• GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients [1.8033500402815792]
  We propose GeoSteer, a manifold-based framework that improves the quality of intermediate reasoning.<n>The method logically consists of: (1) constructing a CoT dataset with step-level scores, (2) training a Variational Autoencoder (VAE) model and a quality estimation model to learn a low-dimensional manifold of high-quality CoT trajectories, and (3) steering hidden states of target LLMs toward higher-quality regions in the latent space.
  arXiv  Detail & Related papers  (2026-01-15T09:44:07Z)
• Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark [124.00111584020834]
  We conduct an empirical study to investigate whether video models are ready to serve as zero-shot reasoners.<n>We focus on the leading and popular Veo-3.<n>We evaluate its reasoning behavior across 12 dimensions, including spatial, geometric, physical, temporal, and embodied logic.
  arXiv  Detail & Related papers  (2025-10-30T17:59:55Z)
• Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models [20.34249941341219]
  We propose a new evaluation framework aimed at assessing the performance of Vision-Language Models (VLMs)<n>We construct a benchmark for spatial deformation reasoning from 2D to 3D.<n>We explore whether the model can effectively perform spatial deformation reasoning from two directions.
  arXiv  Detail & Related papers  (2025-07-01T03:05:56Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• Contrastive Neighborhood Alignment [81.65103777329874]
  We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local topology of the original data in a dimension-reduced space; model distillation, where a small student model is trained to mimic a larger teacher; and legacy model update, where an older model is replaced by a more powerful one.
  arXiv  Detail & Related papers  (2022-01-06T04:58:31Z)

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.