Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution
This addresses the need for more flexible and efficient AI agents, representing a paradigm shift in agent design.
The paper tackles the problem of limited adaptability in AI agents by introducing the ICE strategy for inter-task self-evolution, which reduces API calls by up to 80% and enables GPT-3.5 to match GPT-4's performance on agent tasks.
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.