Models, methods, and the machinery of intelligence.
arXiv
Verdict: NotableSpatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial relation holds, how far an object is, or where to place it.
Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards.
We study how vision-language models (VLMs) can learn to think and actively explore in 3D space.
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets.
Data agents use code to process heterogeneous files and derive analytical insights.
A few well-annotated datasets for land-cover semantic segmentation have recently been introduced to advance the field of earth observation technologies.
The capabilities of an agent swarm depend on both its individual members and how they coordinate.
Looped language models reuse physical Transformer blocks across logical depth, but established architectures entangle recurrence placement, input injection, and recurrent state ....
A general observation in agentic workflows, especially bounded ones, is that the decision space of the LLM, when we separate a decision from generation, starts approaching saturation: the ....