Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
This work addresses the challenge of building general AI agents for continuous learning, though it appears incremental as it builds on existing lifelong learning concepts.
The paper tackles the problem of creating open-ended agents that learn continuously by introducing the Experience-driven Lifelong Learning (ELL) framework, which enables self-evolving agents to grow through real-world interaction, and presents the StuLife benchmark dataset simulating a student's college journey.
As AI advances toward general intelligence, the focus is shifting from systems optimized for static tasks to creating open-ended agents that learn continuously. In this paper, we introduce Experience-driven Lifelong Learning (ELL), a framework for building self-evolving agents capable of continuous growth through real-world interaction. The framework is built on four core principles: (1) Experience Exploration: Agents learn through continuous, self-motivated interaction with dynamic environments, navigating interdependent tasks and generating rich experiential trajectories. (2) Long-term Memory: Agents preserve and structure historical knowledge, including personal experiences, domain expertise, and commonsense reasoning, into a persistent memory system. (3) Skill Learning: Agents autonomously improve by abstracting recurring patterns from experience into reusable skills, which are actively refined and validated for application in new tasks. (4) Knowledge Internalization: Agents internalize explicit and discrete experiences into implicit and intuitive capabilities as "second nature". We also introduce StuLife, a benchmark dataset for ELL that simulates a student's holistic college journey, from enrollment to academic and personal development, across three core phases and ten detailed sub-scenarios. StuLife is designed around three key paradigm