DEALS：面向多智能体LLM系统的去中心化专业知识感知负载服务
DEALS: Decentralized Expertise-Aware Load Serving for Multi-Agent LLM Systems
浏览论文内容
中文总结 AI 辅助
针对多智能体LLM系统集中式协调的可扩展性和适应性局限，提出去中心化低复杂度框架DEALS，通过基于积压量和成功率差异的本地路由实现任务级自我组织和动态负载均衡，提升准确性和吞吐量。
中文摘要 AI 辅助
多智能体系统（MAS）近来已成为一种通过结构化交互协调基于大语言模型（LLM）的智能体以解决复杂任务的有效方法。在实践中，MAS 通常需要处理一系列异构且复杂的任务，要求智能体对每个任务进行分解，然后在共享执行资源的同时，自我组织和自我进化以适应传入的任务。然而，大多数早期的 MAS 方法依赖于集中式控制器或固定的协调模式，这可能限制其可扩展性或适应性。相比之下，现有的去中心化和动态 MAS 通常需要训练专用的路由器或调用 LLM 进行智能体选择，从而导致大量的计算成本和协调开销。为了解决这些挑战，并实现任务级和工作负载级协作的高效任务级自我组织和自我进化，我们提出了去中心化专业知识感知负载服务（DEALS），这是一种去中心化且低复杂度的框架，使智能体能够自我组织并动态路由并发任务进行处理。具体而言，每个智能体维护传入任务的本地队列，其路由器根据积压量和成功率的差异决定是本地处理任务还是将其转发给邻居。同时，执行器在智能体内部和智能体之间并发处理独立任务，部分解决的任务可由其他智能体恢复。实验表明，DEALS 不仅在同质和异质智能体池中沿多个维度（如答案准确性和任务吞吐量）提升了性能，而且以自我组织的方式平衡了智能体的专业知识和负载，实现了有效的去中心化协调。
英文摘要
Multi-agent systems (MAS) have recently emerged as an effective approach for coordinating large language model (LLM)-based agents to solve complex tasks through structured interactions. In practice, MASs often handle a stream of heterogeneous and complex tasks, requiring agents to decompose each task and then self-organize and self-evolve to adapt to incoming tasks while sharing execution resources. However, most early approaches to MASs rely on centralized controllers or fixed coordination patterns, which can limit scalability or adaptability. In contrast, existing decentralized and dynamic MASs often require training dedicated routers or invoking LLMs for agent selection, resulting in substantial computational costs and coordination overhead. To address these challenges and enable efficient task-level self-organization and self-evolution for task- and workload-level collaboration, we propose Decentralized Expertise-Aware Load Serving (DEALS), a decentralized and low-complexity framework that enables agents to self-organize and dynamically route concurrent tasks for processing. Specifically, each agent maintains local queues of incoming tasks, and its router decides whether to process a task locally or forward it to a neighbor based on differences in backlog and success rate. Meanwhile, executors process independent tasks concurrently within and across agents, and partially solved tasks can be resumed by other agents. Experiments show that DEALS not only improves performance along multiple dimensions (e.g., answer accuracy and task throughput) in both homogeneous and heterogeneous agent pools, but also balances agent expertise and workload in a self-organized manner, enabling effective decentralized coordination.
发表机构
- Ohio State University（俄亥俄州立大学）
- University of Colorado at Boulder（科罗拉多大学博尔德分校）
机构由 AI 辅助整理，请以论文原文为准。
