---
title: "Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions"
authors:
  - "Stéphane Aroca-Ouellette"
  - "Miguel Aroca-Ouellette"
  - "Katharina von der Wense"
  - "Alessandro Roncone"
doi: "10.24963/ijcai.2025/457"
url: "https://ijcai.org/proceedings/2025/457"
pdf: "https://ijcai.org/proceedings/2025/0457.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "4101-4109"
track: "Main Track"
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"
---

# Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions

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

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 4101-4109. DOI: [10.24963/ijcai.2025/457](https://doi.org/10.24963/ijcai.2025/457)

## 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.