Evolutionary Framework for Self-Evolving Intelligent Agents: A Review of Recent Advances
Recent comprehensive reviews by researchers from institutions like Princeton, Tsinghua University, and Carnegie Mellon University (CMU) have deconstructed intelligent agent systems into four core components: architecture, models, context, and toolsets. These reviews further break down the evolutionary process into three fundamental dimensions: "What, When, and How," providing a complete framework for research on self-evolving intelligent agents. This framework aims to guide the future development of intelligent agents that can autonomously evolve and adapt to new situations. The reward mechanism plays a crucial role in driving the evolutionary process, and there are four main types of reward-based evolution: text feedback, intrinsic rewards, extrinsic rewards, and implicit rewards. Several representative works explore these categories. For instance, "Reflexion" leverages text feedback to guide agent decision-making, while "CISC" optimizes the inference...