Dieckow, NiklasNiklasDieckowMurena, Pierre-AlexandrePierre-AlexandreMurena2026-06-222026-06-222026-0525th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2026https://hdl.handle.net/11420/63600AI 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.enHuman-AI collaborationtwo-agent collaborationzero-shot assistanceComputer Science, Information and General Works::006: Special computer methods::006.3: Artificial IntelligenceComputer Science, Information and General Works::006: Special computer methods::006.3: Artificial Intelligence::006.33: Knowledge-based SystemsTechnology::600: TechnologyConference Paper10.65109/DFPG9276