让大模型像团队一样协作推理，提速降耗还更准。
The Era of Agentic Organization: Learning to Organize with Language Models
- 用动态分配任务的异步思维协议组织多个模型并行工作
- 推理延迟降低28%，数学题准确率提升，且无需额外训练即可应对新任务
- 适合需要高效多智能体协同的复杂问题求解场景
我们设想了一个新的AI时代——代理型组织，即智能体通过协同并发工作解决复杂问题，实现超越个体智能的成果。为实现这一愿景，我们提出异步思考（AsyncThink）作为大语言模型的新推理范式，将内部思考过程组织为可并发执行的结构。具体而言，我们设计了一种思维协议：由协调者动态分配子任务给工作者，整合中间知识，并生成连贯解决方案。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相比并行思考推理延迟降低28%，同时在数学推理任务上提升准确率；此外，其学习到的异步思考能力具有泛化性，能在未见任务上有效表现而无需额外训练。
原文摘要 · Abstract (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.
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。