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.
Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high cost of interactive…
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets.
Looped Mixture-of-Experts (MoE) models combine parameter reuse with sparse computation to improve performance under matched budgets.
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.
In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users.
Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and widening the navigation interface from ....
The capabilities of an agent swarm depend on both its individual members and how they coordinate.