Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration

TL;DR

This paper introduces MAEL, a framework enabling LLM-based multi-agent systems to learn from cross-task experiences, improving efficiency and solution quality through explicit experience sharing and retrieval.

Contribution

The paper proposes a novel multi-agent cross-task experiential learning framework that enhances generalization and efficiency in LLM-driven multi-agent collaboration.

Findings

Faster convergence in multi-agent tasks.

Higher-quality solutions achieved.

Effective experience retrieval improves reasoning.

Abstract

Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation, resulting in redundant computations and limited generalization across structurally similar tasks. To address this, we introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation. We model the task-solving workflow on a graph-structured multi-agent collaboration network, where agents propagate information and coordinate via explicit connectivity. During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards along with the corresponding inputs and outputs into each agent's individual experience pool. During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step, thereby enabling more accurate and efficient multi-agent collaboration. Experimental results on diverse datasets demonstrate that MAEL empowers agents to learn from prior task experiences effectively-achieving faster convergence and producing higher-quality solutions on current tasks.