Self-evolving Agents with reflective and memory-augmented abilities

TL;DR

This paper introduces a novel framework for self-evolving agents that combines iterative feedback, reflection, and memory optimization to improve multi-tasking and long-term decision-making in AI agents.

Contribution

It presents a new framework integrating feedback, reflection, and memory optimization based on the Ebbinghaus curve, advancing agent capabilities in complex tasks.

Findings

Enhanced multi-tasking performance

Improved long-term decision-making

Effective memory management

Abstract

Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making. In this research, we propose a novel framework by integrating iterative feedback, reflective mechanisms, and a memory optimization mechanism based on the Ebbinghaus forgetting curve, it significantly enhances the agents' capabilities in handling multi-tasking and long-span information.