arXiv:2607. 11818v1 Announce Type: cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents.
arXiv:2607. 01813v1 Announce Type: cross Abstract: Evaluation benchmarks are essential for assessing vision-language models (VLMs), but most multimodal benchmarks are static, making them vulnerable to temporal staleness, data contamination, and costly maintenance.
arXiv:2606. 13239v1 Announce Type: cross Abstract: Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces.
arXiv:2606. 14397v1 Announce Type: new Abstract: As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities.
arXiv:2608. 14047v1 Announce Type: cross Abstract: This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART).
arXiv:2606. 30185v1 Announce Type: new Abstract: Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools.
arXiv:2607. 05465v1 Announce Type: cross Abstract: Complex image creation and editing often require more than a single generation or editing model.
arXiv:2606. 07595v1 Announce Type: cross Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking external tools.
arXiv:2606. 02357v1 Announce Type: cross Abstract: Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools.
arXiv:2607. 15193v1 Announce Type: new Abstract: Graphical user interface (GUI) automation remains challenging in real-world environments, where dynamic layouts, unexpected dialogs, and evolving interface states can cause autonomous agents to drift from user intent.
Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adapts a frozen VLM without any weight updates.
Large language models (LLMs) have demonstrated growing competence in web page generation. However, existing text-driven approaches rely on complex prompts that impose substantial demands on users and offer limited expressivity for page layout and cross-page visual coherence.
arXiv:2606. 00384v1 Announce Type: new Abstract: Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated.