This workshop invites researchers and practitioners to share innovative ideas, explore questions, and discuss strategies to transform the impact of VIS for a future where human and AI agents co-exist.
Abstract
Recent advances in agents (i.e., autonomous, goal-driven AI systems that iteratively observe, act, and learn from their environments) offer a fundamentally different approach from traditional AI models that passively respond to input. These AI agents are rapidly reshaping how we approach data-intensive tasks and providing new opportunities for the VIS community. Imagine an agent autonomously generating visualizations to analyze complex data, discovering patterns collaboratively, testing hypotheses, and communicating visual insights at a speed and scale beyond human capability. Yet, the emergence of these powerful systems raises critical questions that the VIS community must address: Could autonomous agents eventually replace human data scientists, and if not, how might they best collaborate? Are current visualization techniques and interfaces, originally designed for human analysts, suitable for agent interactions? How can VIS designers effectively integrate agents into their workflows without compromising human agency? And to what extent should agents help shape and educate the next generation of visualization researchers? Through a mix of keynote talks, paper presentations, and an agentic VIS challenge, this workshop invites researchers and practitioners to share innovative ideas, explore these questions, and discuss strategies to transform the impact of VIS for a future where human and AI agents co-exist.
Agentic AI systems that reason, plan, and act on complex goals have advanced rapidly across software engineering, scientific discovery, drug development, healthcare, finance, and social simulation. Across these domains a single failure pattern recurs: current systems can execute tasks competently but often struggle to determine when to act, when to pause, when to change strategy, and when to involve a human. Existing reviews catalog agentic architectures, taxonomies, and limitations, but none specify what capabilities these systems must acquire to support dynamic human-AI collaboration. We address that gap. We define collaborative AI as a class of systems that combine generative exploration with autonomous action and calibrate between them based on context, uncertainty, and task demands. We identify four required capabilities: metacognition, contextual mode-switching, uncertainty-aware action, and adaptive human collaboration. We relate these capabilities to established multi-agent systems foundations, including belief-desire-intention architectures, adjustable autonomy, mixed-initiative interaction, and decentralized decision-theoretic control, while specifying the distinct challenges that LLM-based agents introduce. Across the six domains reviewed here, these gaps appear repeatedly and are not solved by current architectures, which positions collaborative AI as a concrete near-term research objective.
Nalan Karunanayake, Savindu Nanayakkara, Kasun Gayashan Hettihewa et al.· International Journal of Net...· 0 citations
AI agents are increasingly adept at tackling complex, long-running tasks. With the rapid surge of autonomous capabilities, human oversight is systematically lagging behind due to limited human-centered interfacing. Aiming to address this, we introduce AgentGUI, a user-friendly, locally hosted GUI for seamlessly observing and steering AI agents amid multiple concurrent, long-running sessions. AgentGUI features 1) rich agent trajectory visualizations, 2) effective manual and automated steering, and 3) integration with and coordination between open-source and frontier agent frameworks. A controlled user study demonstrates statistically significant reduction in the time it takes to identify key elements from agent traces (38% faster, p = 0.023). In a preliminary experiment, AgentGUI's automated drift prevention feature raises the task completion rate of small local agents by as high as 34pp across a 0.8B--9B model ladder (N=50 runs per model). AgentGUI is publicly available through its project website (https://agent-gui-project.github.io) and open-source repository (https://github.com/eth-medical-ai-lab/agent-gui), along with a demo video (https://youtube.com/watch?v=GSDyxN1gTF0).
Xuan Zhao, Jiwoong Sohn, Qinyue Zheng et al.· arXiv.org· 0 citations
The database community is at a pivotal moment. Large Language Models (LLMs) and AI agents are rapidly changing how users interact with data systems. The traditional model—where human experts write SQL queries or navigate complex BI tools—is being disrupted by a new vision: data agents capable of understanding natural language, reasoning about data semantics, autonomously executing multi-step analytical workflows, and collaborating with humans to derive insights. This shift introduces fundamental questions that span database systems, human-computer interaction, AI/ML infrastructure, and programming languages.
This panel will convene leading researchers and practitioners to discuss the future of data agents. A
"data agent"
is defined as an autonomous system capable of perceiving data in various forms (structured, semi-structured, and unstructured), planning and executing complex data manipulation and analysis tasks, interacting with humans through natural language or other intuitive interfaces, and learning from feedback to improve over time. The panel will examine whether this vision is achievable, the technical obstacles that need to be addressed, and how the database community should adapt to meet this emerging challenge.
Guo-Liang Li, Yuyu Luo· Proceedings of the VLDB Endo...· 0 citations
A unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance is presented.
Sparsh Bajoria, Shreyanshu Ranjan, Adhitya M et al.· Cognitive Computation· 0 citations
This work argues that studying AI Scientists as human-agent systems (HAS) is both underexplored and undervalued, and calls for new research that adopts the HAS lens to develop mathematical frameworks for understanding and fostering human-AI synergy in scientific discovery.
P. Emami, Sameera Horawalavithana, T. Nguyễn et al.· 0 citations
This primer draws on fieldwork in a computational biology laboratory to examine what human oversight of AI agents requires in practice and shows that effective oversight has four components: adequate knowledge of system capabilities and limitations, sufficient observation of system actions, meaningful control of system behavior, and timely intervention in system failures.
Samir Passi, Ranjit Singh· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
