智能体组织时代：以语言模型重构组织运作范式

摘要

我们设想一个名为"智能体组织"的人工智能新时代，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，我们提出异步思维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，我们设计了一套思维协议：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，异步思维在提升数学推理准确率的同时，较并行思维降低28%的推理延迟。此外，异步思维能泛化其习得的异步推理能力，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：以语言模型重构组织运作范式

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

摘要

Support