Related papers: FlowForge: Guiding the Creation of Multi-agent Wor…
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…
Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…
Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…
Exploratory search starts with ill-defined goals and involves browsing, learning, and formulating new targets for search. To fluidly support such dynamic search behaviours, we focus on devising interactive visual facets (IVF), visualising…
The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that…
Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the…
Professional designers work from client briefs that specify goals and constraints but often lack concrete design details. Translating these abstract requirements into visual designs poses a central challenge, yet existing tools address…
We introduce the concept of "Design Agents" for engineering applications, particularly focusing on the automotive design process, while emphasizing that our approach can be readily extended to other engineering and design domains. Our…
Dense and versatile image representations underpin the success of virtually all computer vision applications. However, state-of-the-art networks, such as transformers, produce low-resolution feature grids, which are suboptimal for dense…
Generative models have substantially expanded video generation capabilities, yet practical thought-to-video creation remains a multi-stage, multi-modal, and decision-intensive process. However, existing tools either hide intermediate…
Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access…
Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…
Large Language Model (LLM)-powered agents have unlocked new possibilities for automating human tasks. While prior work has focused on well-defined tasks with specified goals, the capabilities of agents in creative design tasks with…
The rapid development of interactive and autonomous AI systems signals our entry into the agentic era. Training and evaluating agents on complex agentic tasks such as software engineering and computer use requires not only efficient model…
Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the…
Datalog-based languages are regaining popularity as a powerful abstraction for expressing recursive computations in domains such as program analysis and graph processing. However, existing systems often face a trade-off between efficiency…
In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…
Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We…
Simulated user agents are increasingly used in usability testing to support fast, iterative UX workflows, as they generate rich data such as action logs and think-aloud reasoning, but the unstructured nature of this output often obscures…
For visualization pedagogy, an important but challenging notion to teach is design, from making to evaluating visualization encodings, user interactions, or data visualization systems. In our previous work, we introduced the design activity…