Self-evolving Agents with reflective and memory-augmented abilities

2024-09-01

arXiv.org

AI Summary

Large language models (LLMs) exhibit limited dynamic adaptability in continuous decision-making and long-horizon, multi-task settings. Method: This paper proposes a self-evolving agent framework that integrates iterative closed-loop feedback, reflective reasoning, and Ebbinghaus forgetting-curve–informed memory optimization to construct a cognition-driven, memory-augmented architecture. This enables dynamic experience filtering, reinforcement, and long-term retention—moving beyond static prompting or fixed memory pools—and supports autonomous agent evolution over ultra-long contexts. Contribution/Results: Experiments demonstrate significant improvements in multi-task coordination stability, decision consistency, and task completion rates. The framework establishes a novel paradigm for developing intelligent agents with human-like continual learning capabilities, advancing the state of adaptive, memory-aware LLM-based agents.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Multiagent Learning
• Machine Learning: Life-Long and Continual Learning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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.

Problem

• Enhancing continuous decision-making in LLMs
• Improving multi-tasking with memory optimization
• Handling long-span information via reflective mechanisms

Innovation

• Self-evolving agents with reflective abilities
• Memory optimization using Ebbinghaus forgetting curve
• Iterative feedback for enhanced multi-tasking