让多个智能体自动调整协作方式和角色，更高效解决复杂问题。
Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts
- 通过动态调整智能体协作结构和角色提示，实现自适应推理。
- 在六项知识密集型任务上平均提升38.69%，且保持高效与泛化能力。
- 适合需要多步推理和跨源整合的复杂问答场景。
多智能体检索增强生成（Multi-agent RAG）通过赋予每个智能体特定角色，支持需多步骤、多来源或复杂推理的难题。然而，现有方法依赖静态行为和固定编排策略，在多样化的多跳任务中表现脆弱。本文识别出两大缺陷：缺乏持续自适应的编排机制，以及个体智能体行为层面的学习缺失。为此，提出HERA框架，联合演化多智能体编排与角色特异性提示。全局层面，基于奖励引导采样与经验积累优化查询相关的智能体拓扑；局部层面，通过信用分配与操作-行为双轴适应，实现角色导向的行为改进。在六个知识密集型基准测试中，HERA相较近期基线平均提升38.69%，同时保持强泛化性与高令牌效率。拓扑分析揭示了涌现的自组织现象，稀疏探索生成紧凑、高价值的多智能体网络，证明其高效协同与稳健推理能力。
原文摘要 · Abstract (English)
Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, supports hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors and fixed orchestration strategies, leading to brittle performance on diverse, multi-hop tasks. We identify two key limitations: the lack of continuously adaptive orchestration mechanisms and the absence of behavior-level learning for individual agents. To this end, we propose HERA, a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts. At the global level, HERA optimizes query-specific agent topologies through reward-guided sampling and experience accumulation. At the local level, Role-Aware Prompt Evolution refines agent behaviors via credit assignment and dual-axes adaptation along operational and behavioral principles, enabling targeted, role-conditioned improvements. On six knowledge-intensive benchmarks, HERA achieves an average improvement of 38.69\% over recent baselines while maintaining robust generalization and token efficiency. Topological analyses reveal emergent self-organization, where sparse exploration yields compact, high-utility multi-agent networks, demonstrating both efficient coordination and robust reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。