arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.08151cs.AIcs.CLcs.MA
收藏

SciAgent：面向通用科学推理的统一多智能体系统

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning

Xuchen Li, Ruitao Wu, Xuanbo Liu, Xukai Wang, Jinbo Hu, Zhixin Bai, Bohan Zeng, Hao Liang, Leheng Chen, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Xu-Yao Zhang,… 展开作者

Xuchen Li, Ruitao Wu, Xuanbo Liu, Xukai Wang, Jinbo Hu, Zhixin Bai, Bohan Zeng, Hao Liang, Leheng Chen, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Xu-Yao Zhang, Liu Liu, Jia Li, Kaiqi Huang, Jiahao Xu, Haitao Mi, Wentao Zhang, Bin Dong

备注：
1. To ensure result rigor, the model outputs require further evaluation by human experts. 2. The results may affect our conclusions and methods, thus necessitating a more detailed review. 3. We anticipate subsequent revisions may be substantial, potentially involving major adjustments to the methodology. Given the uncertainty surrounding the revision process, we decide to request a withdrawal
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有科学推理系统局限且需手工定制的问题，提出统一多智能体系统SciAgent，通过分层协调与专业子智能体协作适配推理策略，在多学科竞赛及基准测试中达人类金牌水平，推动通用科学智能发展。

摘要：

大型语言模型的最新进展使AI系统能在特定领域的科学任务上达到专家级性能，但这些系统仍局限且需手工定制。我们提出SciAgent，一个面向通用科学推理的统一多智能体系统——其具备跨学科和难度级别适配推理策略的能力。SciAgent将问题解决组织为分层过程：协调智能体解释每个问题的领域和复杂度，动态编排专业工作系统，每个系统由负责符号推导、概念建模、数值计算和验证的交互推理子智能体组成。这些智能体协作构建并优化针对各任务的推理管道。在数学和物理奥林匹克竞赛（IMO、IMC、IPhO、CPhO）中，SciAgent持续达到或超越人类金牌得主的性能，展现了领域通用性和推理适应性。此外，SciAgent在国际化学奥林匹克竞赛（IChO）和人类终极考试（HLE）基准的精选问题上进行了测试，进一步证实了系统跨多样科学领域的泛化能力。该工作将SciAgent确立为迈向通用科学智能的具体一步——即能在专家级别进行连贯跨学科推理的AI系统。

英文摘要：

Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcrafted. We introduce SciAgent, a unified multi-agent system designed for generalistic scientific reasoning-the ability to adapt reasoning strategies across disciplines and difficulty levels. SciAgent organizes problem solving as a hierarchical process: a Coordinator Agent interprets each problem's domain and complexity, dynamically orchestrating specialized Worker Systems, each composed of interacting reasoning Sub-agents for symbolic deduction, conceptual modeling, numerical computation, and verification. These agents collaboratively assemble and refine reasoning pipelines tailored to each task. Across mathematics and physics Olympiads (IMO, IMC, IPhO, CPhO), SciAgent consistently attains or surpasses human gold-medalist performance, demonstrating both domain generality and reasoning adaptability. Additionally, SciAgent has been tested on the International Chemistry Olympiad (IChO) and selected problems from the Humanity's Last Exam (HLE) benchmark, further confirming the system's ability to generalize across diverse scientific domains. This work establishes SciAgent as a concrete step toward generalistic scientific intelligence-AI systems capable of coherent, cross-disciplinary reasoning at expert levels.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑