arXiv:2608. 07955v1 Announce Type: new Abstract: Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial perception and fine-grained geometric computation beyond end-to-end generation.
arXiv:2608.12743v3 Announce Type: replace Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ab...
arXiv:2606. 13673v1 Announce Type: cross Abstract: Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs).
arXiv:2608. 12743v1 Announce Type: new Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants.
arXiv:2610.01999v1 Announce Type: new Abstract: Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities ac...
arXiv:2606. 12830v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction.
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
SpatialBrain is a framework that enhances spatial reasoning by retaining experience about when to observe, reconstruct, measure, or change reference frames while keeping its vision-language backbone unchanged. It fuses current observations into queryable spatial relations, offers reusable tool procedures through a Spatial Skill Library, and associates task conditions with experience via Spatial Cognition. The system abstracts completed trajectories into process records, consolidating knowledge across task blocks to inform future decisions without transferring scene coordinates or reference answers, and demonstrates improved performance on four out of five spatial-reasoning benchmarks.
The paper introduces EvoSkill-GUI, a training‑free framework that enables GUI agents to evolve their skills during deployment. Each skill is packaged with metadata, executable plans, and recovery rules, and the system follows a reflect‑revise‑reuse loop where the agent instantly revises skills based on execution feedback. Experiments on MobileWorld, AndroidWorld, and OSWorld show consistent performance gains up to +16.2% without any additional training.
arXiv:2608. 05573v1 Announce Type: new Abstract: LLM agents increasingly execute long-horizon tasks through tool use and environment interaction, shifting evaluation from final-response scoring to verification of complete executions.
arXiv:2608. 10494v1 Announce Type: new Abstract: Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence.
LLM agents increasingly execute long-horizon tasks through tool use and environment interaction, shifting evaluation from final-response scoring to verification of complete executions. For skill-augmented agents, verification additionally requires the procedural knowledge encoded in task-time skills, because this knowledge indicates what evidence to inspect and which failures are task-critical.