Adaptive Agents for Mixed-Initiative Human-AI Collaborations
Abstract
Efficient human-agent collaboration requires understanding each other’s capabilities and establishing appropriate reliance. My thesis focuses on optimizing performance in mixed-initiative settings, where humans and agents dynamically contribute to decisions and actions. I first explore key factors shaping human reliance on decision-support agents, then examine how agents can model this reliance to initiate actions. My proposed work aims to enable agents to jointly provide decision and action support in multi-objective tasks, using bi-directional communication to enhance collaboration.
Cite
Text
Natarajan. "Adaptive Agents for Mixed-Initiative Human-AI Collaborations." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35220Markdown
[Natarajan. "Adaptive Agents for Mixed-Initiative Human-AI Collaborations." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/natarajan2025aaai-adaptive/) doi:10.1609/AAAI.V39I28.35220BibTeX
@inproceedings{natarajan2025aaai-adaptive,
title = {{Adaptive Agents for Mixed-Initiative Human-AI Collaborations}},
author = {Natarajan, Manisha},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {29285-29286},
doi = {10.1609/AAAI.V39I28.35220},
url = {https://mlanthology.org/aaai/2025/natarajan2025aaai-adaptive/}
}