智能体组织时代：学会运用语言模型构建组织

摘要

我们设想一个名为"智能体组织"的AI新时代，其中智能体通过协同并行的方式解决复杂问题，实现超越个体智能的成果。为实现这一愿景，我们引入异步思维（AsyncThink）作为大语言模型推理的新范式，将内部思考过程组织为可并发执行的结构。具体而言，我们提出一种思维协议：组织者动态分配子问题给工作单元，整合中间知识，最终生成连贯解决方案。更重要的是，该协议中的思维结构可通过强化学习进一步优化。实验表明，AsyncThink在数学推理任务上不仅准确率提升，推理延迟较并行思维降低28%。此外，AsyncThink能泛化其习得的异步思维能力，无需额外训练即可有效处理未见任务。

English

We envision a new era of AI, termed agentic organization, where agents solve complex problems by working collaboratively and concurrently, enabling outcomes beyond individual intelligence. To realize this vision, we introduce asynchronous thinking (AsyncThink) as a new paradigm of reasoning with large language models, which organizes the internal thinking process into concurrently executable structures. Specifically, we propose a thinking protocol where an organizer dynamically assigns sub-queries to workers, merges intermediate knowledge, and produces coherent solutions. More importantly, the thinking structure in this protocol can be further optimized through reinforcement learning. Experiments demonstrate that AsyncThink achieves 28% lower inference latency compared to parallel thinking while improving accuracy on mathematical reasoning. Moreover, AsyncThink generalizes its learned asynchronous thinking capabilities, effectively tackling unseen tasks without additional training.

智能体组织时代：学会运用语言模型构建组织

The Era of Agentic Organization: Learning to Organize with Language Models

摘要

Support