360$^\circ$REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System
This addresses performance enhancement for multi-agent systems based on large language models, though it appears incremental by building on existing evaluation and reflection methods.
The paper tackles the problem of improving multi-agent system performance by proposing a hierarchical framework with 360° assessment and dual-level experience accumulation, achieving state-of-the-art results on complex task datasets.
Large language model agents have demonstrated remarkable advancements across various complex tasks. Recent works focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. Since these agents are all based on the same LLM, only conducting self-evaluation or removing underperforming agents does not substantively enhance the capability of the agents. We argue that a comprehensive evaluation and accumulating experience from evaluation feedback is an effective approach to improving system performance. In this paper, we propose Reusable Experience Accumulation with 360$^\circ$ Assessment (360$^\circ$REA), a hierarchical multi-agent framework inspired by corporate organizational practices. The framework employs a novel 360$^\circ$ performance assessment method for multi-perspective performance evaluation with fine-grained assessment. To enhance the capability of agents in addressing complex tasks, we introduce dual-level experience pool for agents to accumulate experience through fine-grained assessment. Extensive experiments on complex task datasets demonstrate the effectiveness of 360$^\circ$REA.