1st International Workshop on Agentic AI for Big Data
AAI-BD 2026 will be held in conjunction with IEEE Big Data 2026 and the Cross-AI Pre-Conference Symposium 2026.
Introduction
The rise of agentic AI marks a fundamental shift in how Big Data is leveraged and governed. By autonomously reasoning over vast and complex datasets, agentic AI moves Big Data beyond storage and analytics toward self-directed intelligence, enabling real-time insight generation, adaptive decision-making, and continuous evolution of data-driven systems at global scale.
AAI-BD is the first workshop in the world dedicated to this emerging area, bringing together leading researchers, practitioners, and industry experts to explore architectures, algorithms, and applications of autonomous AI systems for Big Data. It provides a high-impact forum to advance research, foster cross-disciplinary collaboration, and define the future of agentic AI in large-scale data-driven environments.
The workshop focuses on novel AI models, multi-agent systems, distributed AI architectures, and edge AI integration, with applications across domains such as finance, healthcare, IoT, robotics, smart cities, transportation, cybersecurity, environmental science, supply chain management, GIS, and creative and physical domains including arts, music, dance, and sports. It aims to spark discussion on scalable and autonomous AI systems, attract high-quality submissions bridging theoretical foundations and practical implementations, and highlight emerging challenges and transformative opportunities in the design, deployment, and evaluation of agentic AI systems.
Topics
This open call for papers invites original contributions on theory, methods, architectures, and applications of agentic AI for Big Data. Submissions may focus on technical, conceptual, or applied research, including but not limited to the areas below.
Technical topics and methods
- Architectures for agentic AI on Big Data
- Autonomous multi-agent systems for data-intensive tasks
- AI agents using distributed or NoSQL databases as memory
- Integration of LLMs, generative AI, and multimodal AI in autonomous agents
- Edge AI for real-time autonomous decision-making
- Distributed and federated agentic AI systems
- Agentic AI for autonomous data curation and cleaning
- Explainability, interpretability, and trust in agentic AI systems
- Evaluation frameworks, benchmarks, and performance metrics for agentic AI
- Resource-efficient AI for large-scale data processing
- Human-AI collaboration in autonomous systems
- Security, privacy, and ethical considerations in agentic AI
- Reinforcement learning and planning in multi-agent Big Data environments
- Simulation-based testing for autonomous AI in data-rich contexts
Applications
| Domain | Directions |
|---|---|
| Robotics | Multi-robot coordination, autonomous exploration, adaptive task planning |
| Arts & Entertainment | AI-generated music, dance choreography, sports analytics, performance optimization, creative AI applications |
| Cybersecurity | Autonomous threat detection, anomaly identification, automated response systems |
| Digital Content & Social Media | Automated content analysis, misinformation detection, recommendation systems |
| Finance | Automated trading, risk assessment, fraud detection, portfolio optimization |
| Healthcare | Clinical decision support, autonomous medical imaging analysis, patient monitoring |
| Internet of Things (IoT) | Intelligent sensor networks, real-time edge processing, predictive maintenance |
| Transportation | Autonomous vehicle coordination, route optimization, traffic prediction, logistics planning |
| Smart Cities | Traffic management, energy optimization, urban planning using Big Data |
| Geographic Information Systems (GIS) | Autonomous spatial data analysis, urban modeling, mapping, environmental monitoring |
| Supply Chain & Logistics | Autonomous inventory management, demand prediction, route optimization |
| Scientific Research | Autonomous analysis of large-scale experimental data, genomics, high-energy physics datasets |
| Environmental Science | Climate modeling, ecosystem monitoring, disaster prediction and response |
| Education | Personalized learning platforms, intelligent tutoring systems, data-driven curriculum optimization |
Important Dates
| Date | Milestone |
|---|---|
| October 12, 2026 | Full paper submission (8–10 pages) |
| October 19, 2026 | Short paper submission (5–7 pages) |
| October 26, 2026 | Poster paper submission (3–4 pages) |
| November 2, 2026 | Poster acceptance notification |
| November 14, 2026 | Video submission |
| November 14, 2026 | Camera-ready submission deadline |
| November 14, 2026 | Author registration deadline |
| December 14-16, 2026 | Cross-AI Pre-Conference Symposium & IEEE Big Data Workshops |
Submission
1. Papers
Papers follow the IEEE conference manuscript templates (Overleaf or US Letter), in English, as PDF, and are reviewed double-blind.
| Category | Length (including references) |
|---|---|
| Full paper | 8–10 pages |
| Short paper | 5–7 pages |
| Poster paper | 3–4 pages |
2. Presentation videos
Accepted submissions provide a pre-recorded video.
| Category | Presentation | Q&A |
|---|---|---|
| Full paper | 15 minutes | 3 minutes |
| Short paper | 10 minutes | 2 minutes |
| Poster | 6 minutes | 2 minutes |
All submissions are made through the AirBalloon conference management system and evaluated through a unified process. Upon acceptance, authors may choose to publish in the IEEE Big Data conference proceedings or the indexed Cross-AI conference proceedings, with the corresponding registration fees. Please refer to the respective official registration pages for current fees and registration details. At least one author must register for the corresponding event for the paper/abstract to be published.
Program Chairs
- Lindi Liao, George Mason University, USA (Chair)
- Callie C. Liao, Stanford University, USA (Co-Chair)
Program Committee
- Zhiqian Chen, Mississippi State University, USA
- Kaiqun Fu, Texas Christian University, USA
- Maryam Heidari, George Mason University, USA
- Fanchun Jin, Google Inc., USA
- Ge Jin, Purdue University, USA
- Ahmad Mousavi, American University, USA
- Abhimanyu Mukerji, Amazon, USA
- Chen Shen, Google Inc., USA
- Gregory Joseph Stein, George Mason University, USA
- Yingfan Xu, Oklahoma State University, USA
- Alex Wang, Yale University, USA
- Zhenwei Zhang, University of Maryland, USA
If you are interested in serving on the workshop program committee or paper reviewing, please contact the Workshop Chair.