...The project focuses on enabling agents to improve their behavior through interactive learning rather than relying solely on static prompts or predefined skills. One of its key ideas is allowing users to train an AI agent simply by interacting with it conversationally, using natural language feedback to guide the learning process. The system incorporates reinforcement learning techniques to refine the agent’s policies for tool use, decision making, and task completion over time. It also explores approaches such as online policy distillation and hindsight feedback signals to strengthen training signals from real interactions. The framework operates asynchronously and does not require external API keys, making it easier to experiment with local agent training workflows.