SwarmSys：基于去中心化群体智能代理的可扩展自适应推理系统

摘要

大型语言模型（LLM）代理已展现出卓越的推理能力。然而，现有的多代理框架往往依赖固定角色或集中控制，限制了在长期推理中的可扩展性和适应性。我们引入了SwarmSys，一个受群体智能启发的分布式多代理推理闭环框架。在SwarmSys中，协调通过三个专门角色——探索者、工作者和验证者——之间的迭代互动自然涌现，这些角色持续循环于探索、利用和验证之中。为实现可扩展且自适应的协作，我们整合了自适应代理与事件档案、基于嵌入的概率匹配以及一种受信息素启发的强化机制，支持动态任务分配与无需全局监督的自组织收敛。在符号推理、研究综合及科学编程任务中，SwarmSys均显著超越基线模型，提升了准确性与推理稳定性。这些发现表明，受群体启发的协调机制为可扩展、鲁棒且自适应的多代理推理提供了一个有前景的范式，暗示协调扩展或可与模型扩展并驾齐驱，共同推动LLM智能的发展。

English

Large language model (LLM) agents have shown remarkable reasoning abilities. However, existing multi-agent frameworks often rely on fixed roles or centralized control, limiting scalability and adaptability in long-horizon reasoning. We introduce SwarmSys, a closed-loop framework for distributed multi-agent reasoning inspired by swarm intelligence. Coordination in SwarmSys emerges through iterative interactions among three specialized roles, Explorers, Workers, and Validators, that continuously cycle through exploration, exploitation, and validation. To enable scalable and adaptive collaboration, we integrate adaptive agent and event profiles, embedding-based probabilistic matching, and a pheromone-inspired reinforcement mechanism, supporting dynamic task allocation and self-organizing convergence without global supervision. Across symbolic reasoning, research synthesis, and scientific programming tasks, SwarmSys consistently outperforms baselines, improving both accuracy and reasoning stability. These findings highlight swarm-inspired coordination as a promising paradigm for scalable, robust, and adaptive multi-agent reasoning, suggesting that coordination scaling may rival model scaling in advancing LLM intelligence.

SwarmSys：基于去中心化群体智能代理的可扩展自适应推理系统

SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning

摘要

Support