Sycophancy in Language Models: A Survey Across Behaviors and Topologies

Sycophancy, the tendency of language models to prioritize user agreement over truthful, independent response, spans a fragmented literature across measurement, mechanism, and mitigation. The argument is that sycophancy is not one behavior but a family of distinct compliance behaviors whose form depends on how the interaction is structured, a dependence termed topology-modulation: the same behavior is measured, mitigated, and fails differently in single-turn, multi-turn, multi-agent, and tool-using settings. Organizing 126 papers by what the model does, where it occurs, and why it arises shows that evaluation concentrates in single-turn settings even as deployment moves toward multi-turn and tool-use.