Suggestion-based assistance of suboptimal users in sequential decision-making tasks
Publikationstyp
Conference Paper
Date Issued
2026-05
Sprache
English
Start Page
3402
End Page
3404
Citation
25th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2026
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
Association for Computing Machinery (ACM)
ISBN of container
979-8-4007-2317-9
AI agents can assist humans by offering suggestions which users may accept or reject. This creates an asymmetric collaboration where the user retains full control while the AI lacks direct agency. We demonstrate that merely suggesting task-optimal actions can yield worse outcomes than unassisted performance; effective assistance requires understanding the user’s decision-making. To address this, we propose a zero-shot method based on Bayesian estimation of the user’s acceptance and fallback behavior, relying on a parametric model rather than prior data. We validate our approach theoretically and empirically on a novel toy environment, assessing its performance against baselines and stability in situations where parameters are incorrectly estimated.
Subjects
Human-AI collaboration
two-agent collaboration
zero-shot assistance
DDC Class
006.3: Artificial Intelligence
006.33: Knowledge-based Systems
600: Technology