A new diagnostic benchmark decomposes LLM spatial navigation into three cognitive scales and shows that cross-scale aggregation, not single-level deficits, causes failure beyond small mazes.
Does spatial cognition emerge in frontier models?
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
SpatialAct benchmark shows VLMs handle isolated spatial reasoning but fail to maintain coherent spatial beliefs and produce reliable actions in multi-turn 3D interactions, underperforming humans.
CVSBench benchmark shows VLMs struggle with cross-view spatial consistency but improve substantially when given 3D scene imagination inputs.
FESTS uses Spatial Regular Expressions compiled from queries to generate 27k training tuples that raise a 3B-parameter LLM's frame-level F1 on spatio-temporal video reasoning from 48.5% to 87.5%, matching GPT-4.1 while staying far smaller.
LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
Multi-SpatialMLLM integrates depth perception, visual correspondence, and dynamic perception into MLLMs via a 27M-sample MultiSPA dataset and benchmark, yielding gains on multi-frame spatial tasks.
MLLMs achieve competitive but subhuman performance on the new VSI-Bench for visual-spatial intelligence from videos, with spatial reasoning as the main bottleneck and explicit cognitive map generation improving distance estimation.
AlloSpatial adds structured allocentric priors and a harness for tool-use and arbitration to improve spatial reasoning in foundation models, with 5-18% gains on VSI-Bench and MindCube in training-free settings and further gains after RL internalization.
citing papers explorer
-
Lost in Aggregation: A Multi-Scale Diagnostic Benchmark for LLM Spatial Navigation
A new diagnostic benchmark decomposes LLM spatial navigation into three cognitive scales and shows that cross-scale aggregation, not single-level deficits, causes failure beyond small mazes.
-
SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
SpatialAct benchmark shows VLMs handle isolated spatial reasoning but fail to maintain coherent spatial beliefs and produce reliable actions in multi-turn 3D interactions, underperforming humans.
-
CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming
CVSBench benchmark shows VLMs struggle with cross-view spatial consistency but improve substantially when given 3D scene imagination inputs.
-
Spatio-Temporal Grounding of Large Language Models from Perception Streams
FESTS uses Spatial Regular Expressions compiled from queries to generate 27k training tuples that raise a 3B-parameter LLM's frame-level F1 on spatio-temporal video reasoning from 48.5% to 87.5%, matching GPT-4.1 while staying far smaller.
-
Artificial Phantasia: Emergent Mental Imagery in Large Language Models
LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
-
Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
Multi-SpatialMLLM integrates depth perception, visual correspondence, and dynamic perception into MLLMs via a 27M-sample MultiSPA dataset and benchmark, yielding gains on multi-frame spatial tasks.
-
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
MLLMs achieve competitive but subhuman performance on the new VSI-Bench for visual-spatial intelligence from videos, with spatial reasoning as the main bottleneck and explicit cognitive map generation improving distance estimation.
-
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
AlloSpatial adds structured allocentric priors and a harness for tool-use and arbitration to improve spatial reasoning in foundation models, with 5-18% gains on VSI-Bench and MindCube in training-free settings and further gains after RL internalization.