Proceedings

Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions

Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette, Katharina von der Wense, Alessandro Roncone

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 4101-4109.

https://doi.org/10.24963/ijcai.2025/457

Keywords

  • Agent-based and Multi-agent Systems: MAS: Human-agent interaction
  • Agent-based and Multi-agent Systems: MAS: Coordination and cooperation
  • Humans and AI: HAI: Human-AI collaboration

Abstract

In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a mechanism humans rely on to implicitly align with teammates. To address this gap, we introduce HA^2: Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA^2 in the Overcooked environment, demonstrating statistically significant improvement over existing baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming all state-of-the-art methods.

Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette, Katharina von der Wense, and Alessandro Roncone. 2025. Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 4101–4109. https://doi.org/10.24963/ijcai.2025/457
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards