This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy
for enhancing the adaptability and flexibility of AI agents through inter-task
self-evolution. Unlike existing methods focused on intra-task learning, ICE
promotes the transfer of knowledge between tasks for genuine self-evolution,
similar to human experience learning. The strategy dynamically investigates
planning and execution trajectories, consolidates them into simplified
workflows and pipelines, and exploits them for improved task execution. Our
experiments on the XAgent framework demonstrate ICE's effectiveness, reducing
API calls by as much as 80% and significantly decreasing the demand for the
model's capability. Specifically, when combined with GPT-3.5, ICE's performance
matches that of raw GPT-4 across various agent tasks. We argue that this
self-evolution approach represents a paradigm shift in agent design,
contributing to a more robust AI community and ecosystem, and moving a step
closer to full autonomy.

通过 Investigate-Consolidate-Exploit（ICE）策略，本文介绍了一种提高 AI 代理的适应性和灵活性的新方法。与现有的针对任务内学习的方法不同，ICE 促进了任务间知识的转移，实现了真正的自我演化，类似于人类的经验学习。通过动态调查、整合简化工作流程和流水线，并利用它们改进任务执行，我们在 XAgent 框架上的实验证明了 ICE 的有效性，将 API 调用量减少了 80％，并显著降低了模型能力的需求。尤其是与 GPT-3.5 结合使用时，ICE 在各种代理任务上的性能与原始 GPT-4 相匹配。我们认为这种自我演化的方法代表了代理设计的范式转变，为更健壮的 AI 社区和生态系统做出了贡献，距离完全自主更近了一步。