{"type":"ScholarlyArticle","title":"Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions","authors":[{"name":"Stéphane Aroca-Ouellette","slug":"stephane-aroca-ouellette","given":"Stéphane","family":"Aroca-Ouellette","affiliation":""},{"name":"Miguel Aroca-Ouellette","slug":"miguel-aroca-ouellette","given":"Miguel","family":"Aroca-Ouellette","affiliation":""},{"name":"Katharina von der Wense","slug":"katharina-von-der-wense","given":"Katharina","family":"von der Wense","affiliation":""},{"name":"Alessandro Roncone","slug":"alessandro-roncone","given":"Alessandro","family":"Roncone","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/457","url":"https://ijcai.org/proceedings/2025/457","pdf":"https://ijcai.org/proceedings/2025/0457.pdf","markdown":"https://ijcai.org/proceedings/2025/457.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/457","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Humans and AI","track":"Main Track","number":457,"pages":{"first":4101,"last":4109},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}