360∘REA: Towards A Reusable Experience Accumulation with 360∘ Assessment for Multi-Agent System

2024-04-08

Findings of the Association for Computational Linguistics ACL 2024

AI Summary

Multi-agent systems face performance bottlenecks in complex tasks due to coarse-grained evaluation and poor reusability of learned experience. Method: We propose an evaluation-driven, reusable experience accumulation framework featuring a novel 360° fine-grained multi-dimensional evaluation mechanism, a hierarchical multi-agent architecture, a dual-level experience pool (with structured storage and semantic retrieval), and an LLM-powered self-reflection and experience distillation module—enabling a closed “evaluation–feedback–evolution” loop. Contribution/Results: This work pioneers the integration of an organized evaluation paradigm into multi-LLM collaborative systems, significantly enhancing long-term team performance and cross-task generalization. Extensive experiments across multiple complex task benchmarks demonstrate consistent and substantial improvements over state-of-the-art baselines, validating both the effectiveness and scalability of evaluation-driven experience accumulation.

Technology Category

• Multiagent Systems: Multiagent Learning
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• 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 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.

Problem

• Enhance multi-agent system performance through comprehensive evaluation.
• Accumulate reusable experience using fine-grained assessment feedback.
• Improve agent capability in complex tasks with hierarchical framework.

Innovation

• Hierarchical multi-agent framework for complex tasks
• 360-degree performance assessment for multi-perspective evaluation
• Dual-level experience pool for agent capability enhancement