Related papers: VisDocSketcher: Towards Scalable Visual Documentat…
Drug discovery frequently loses momentum when data, expertise, and tools are scattered, slowing design cycles. To shorten this loop we built a hierarchical, tool using agent framework that automates molecular optimisation. A Principal…
Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current…
While Multimodal Large Language Models (MLLMs) excel at visual understanding, they often struggle in complex scenarios that require visual planning and imagination. Inspired by how humans use sketching as a form of visual thinking to…
The visual analytics community has long aimed to understand users better and assist them in their analytic endeavors. As a result, numerous conceptual models of visual analytics aim to formalize common workflows, techniques, and goals…
Translating natural language to visualization (NL2VIS) has shown great promise for visual data analysis, but it remains a challenging task that requires multiple low-level implementations, such as natural language processing and…
The evaluation of large language models (LLMs) has predominantly relied on static datasets, which offer limited scalability and fail to capture the evolving reasoning capabilities of recent models. To overcome these limitations, we propose…
Large language model (LLM) agents are increasingly capable of orchestrating complex tasks in low-code environments. However, these agents often exhibit hallucinations and logical inconsistencies because their inherent reasoning mechanisms…
Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…
We present a Collaborative Agent-Based Framework for Multi-Image Reasoning. Our approach tackles the challenge of interleaved multimodal reasoning across diverse datasets and task formats by employing a dual-agent system: a language-based…
Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting…
Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on crafting multi-agent systems with agentic workflows, where…
Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrinsics, as…
Scientific data visualization is pivotal for transforming raw data into comprehensible visual representations, enabling pattern recognition, forecasting, and the presentation of data-driven insights. However, novice users often face…
Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry…
Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…
The rapid advancement of Multimodal Large Language Models (MLLMs) has enabled browsing agents to acquire and reason over multimodal information in the real world. But existing benchmarks suffer from two limitations: insufficient evaluation…
Accurate visual understanding is imperative for advancing autonomous systems and intelligent robots. Despite the powerful capabilities of vision-language models (VLMs) in processing complex visual scenes, precisely recognizing obscured or…
Video production workflows offer a rich and demanding arena for evaluating multimodal AI agents: they require composite capabilities across text, image, audio, and video understanding, along with long-horizon planning, and tool use. To this…
Hand-drawn sketches are a natural and efficient medium for capturing and conveying ideas. Despite significant advancements in controllable natural image generation, translating freehand sketches into structured, machine-readable diagrams…
Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill…