How Can We Trust and Control Agentic AI? Toward Alignment, Robustness, and Verifiability in Autonomous LLM Agents
About the Workshop
Agentic AI marks a new frontier for artificial intelligence: systems that move beyond static prediction to autonomous reasoning, tool use, and sustained collaboration with humans and society. These agents hold the potential to transform healthcare, education, robotics, and enterprise automation. Realizing this promise requires not only technical advances, but also ensuring that such systems remain aligned with human values, resilient under real-world complexity, and verifiable in ways that inspire lasting trust and effective control.
The AAAI 2026 Workshop on Trust and Control in Agentic AI convenes leading voices from research, industry, and policy to shape this agenda. We invite contributions that advance the principles and practice of alignment, robustness, and verifiability in agentic systems, spanning core algorithms, evaluation methods, institutional frameworks, and governance. By fostering cross-disciplinary dialogue and catalyzing new collaborations, the workshop aims to chart pathways for deploying agentic AI responsibly and at scale, ensuring that its benefits are realized broadly and equitably.
Schedule
All times are in Singapore Time (SGT)
Invited Speakers
Yewen (Evan) Pu
Nanyang Technological University, Singapore
Matthew E. Taylor
University of Alberta, Canada
Jiafei Duan
University of Washington, USA
Stefano Albrecht
University of Edinburgh, Scotland
Chi Zhang
Westlake University, China
Organizers
Haiyan Yin
CFAR, A*STAR, Singapore
Joey Tianyi Zhou
CFAR, A*STAR, Singapore
Sebastian Tschiatschek
University of Vienna, Austria
Piotr Koniusz
Data61, CSIRO; Australian National University, Australia
Simon See
NVIDIA AI Technology Center, USA
Advisory & Extended Committee
Yew-Soon Ong
Advisory Board
Ivor Tsang
Advisory Board
Xu Cong
Advisory Board
Yueming Lyu
Workflow Chair
NG Aik Beng
Industry Chair
Megani Rajendran
Industry Outreach Committee
Timothy Liu
Industry Outreach Committee
Call for Papers
We invite submissions on advancing trust and control in agentic AI, with a focus on alignment, robustness, and verifiability.
- Trustworthy planning and control in agentic systems
- Verification and auditable behavior of agentic LLMs
- Personalized agents and consistent persona modeling
- Safety-critical embodied agentic AI
- Human-centric alignment and feedback integration
- Human oversight and control in agentic workflows
- Evaluating and benchmarking trust in agentic LLMs
- Governance, transparency, and accountability frameworks
Submission Requirements:
Submissions must be prepared using the AAAI 2026 template. We accept research papers (novel algorithms, theory, or experiments), position papers (provocative perspectives on agentic AI), and survey papers.
- Long papers: up to 7 pages of technical content, plus 1 page for references
- Short papers: up to 4 pages of technical content, plus 1 page for references