Human-Centered Agentic AI

FIT 2026

Track 10: Human-Centered Agentic AI

Track Chair:
1. Sidra Zafar, Kinnaird College for Women, Lahore, Pakistan

Track Co-Chair:
1. Aasia Khanum, Forman Christian College University, Lahore, Pakistan 2. Zeeshan Zia, Chief Scientist, Retrocausal, Inc. Seattle, USA

The track aims to target research on the next generation of Autonomous Agents that are able to plan, call  out tools, retain memory, and interact with the world with minimal human interaction. We particularly welcome papers on pragmatic deployments in real-world domains, multi-agent coordination, adversarial security threats specific to agentic pipelines, safety and alignment mechanisms, calibrated human trust and explainability, and ethics and governance of delegating consequential decisions to AI systems. 

Topics of interest include, but are not limited to: 

  1. Agentic Systems for Real-World Domain Applications
  2. Multi-Agent Orchestration and Communication Architectures 
  3. Dynamic and Adaptive Multi-Agent Systems 
  4. Prompt Injection, Agent Hijacking and Tool Poisoning. 
  5. Agentic Pipelines Adversarial Detection and Defense 
  6. Safety Constraints, Guardrails and Human Oversight: 
  7. Accountability, Regulation and Policy for Agentic AI 
  8. Localization and Resource-Constrained Deployment of Agentic AI in Global South. 
  9. Trust, Explainability and Human Agent Interaction 
  10. Delegation Boundaries and Human-Agent Collaboration Models 
  11. Benchmarking, Evaluation and Robustness of Agentic systems. 
  12. Novel Agentic Architectures, Engineering Approaches and Design Patterns