Large language agents have achieved considerable performance across various agentic planning tasks. However, most current agent learning methods are spoon-feeding, with gold trajectories, external feedback and knowledge mindlessly feeding into agent models regardless of their actual needs, resulting in a lack of self-consciousness during the planning process. In this paper, we introduce KnowSelf, a data-centric approach that enables agents to have knowledgeable self-awareness similar to humans, selectively self-correcting and querying knowledge based on certain situations during the planning process. Concretely, we devise a heuristic situation judgement criterion to mark special tokens on the agent’s self-explored trajectories for collecting training data. Through a two-stage training process, the agent model can switch between different situations by generating specific special tokens, achieving optimal planning effects with minimal costs. Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge. We also present further analysis to examine the effectiveness of agentic knowledgeable self-awareness from different aspects.