SCION：面向智能体时代的科学发现操作系统
Rethinking Scientific Discovery in the Agentic Era
论文提出 SCION（Scientific Collaborative Innovation with Agentic Organizational Nexus），一个作为“组织枢纽”的智能体科学操作系统，通过 Science Agent 充当 Meta-Harness，把科学任务、工具、智能体、产物与记忆连接成可执行、可审计、可复用的研究流程。
Authors:Yining Zheng, Yuxin Wang, Jiahao Lu, Shicheng Fang, Weiyi Wang, Yongzhuo Yang, Bowen Li, Haochen Ma, Chen Hu, Bowen Chen, Yang Wang, Huanhui Chen, Yitong Chen, Jiajun Chen, Zhiyuan Li, Yanlin Li, Zhuo Yang, Qifeng Wu, Jiaying He, Zhijie Jinluo, Xiaohu Xu, Yi Feng, Juncheng Qian, Yizhou Chen, Yang Cheng, Tong Zhu, Tianlei Ying, Hongyu Yu, Hongjun Xiang, Xipeng Qiu
Abstract:Artificial intelligence has advanced scientific discovery, but most AI4Science systems remain fragmented tools that rely on humans to coordinate problem formulation, literature grounding, model use, simulation, validation, and knowledge reuse. This paper presents \textbf{SCION (Scientific Collaborative Innovation with Agentic Organizational Nexus)}, an agentic scientific operating system that acts as an \textbf{organizational nexus}. Through a Science Agent serving as a \textbf{Meta-Harness}, SCION connects scientific tasks, tools, agents, artifacts, and memory, transforming research into an executable, auditable, and reusable operational process. At its core is the \textbf{Research Execution Plan (REP)}, which compiles high-level scientific intent into staged objectives, dependencies, verification checkpoints, tool requirements, expected artifacts, and fallback conditions. SCION further integrates hierarchical multi-agent execution, profile-driven specialization, selective context construction, governed delegation, and layered epistemic memory to support long-horizon scientific work. We formulate discovery under SCION as \textbf{Target-conditioned Inverse Search} and extend it to hidden-target settings through batch active search under finite experimental budgets. Applications in materials analysis, molecule design, and protein or antibody screening, together with experiments on scientific reading, idea generation, molecule generation, and antibody screening, show that SCION outperforms existing autonomous research-agent baselines, especially in decomposition, verification, refinement, and memory reuse. Overall, SCION shifts AI from isolated tools toward a coordinated operational layer for traceable and reusable scientific innovation.
| Comments: | 26 pages, 7 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.03863 [cs.CL] |
| (or arXiv:2607.03863v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.03863 arXiv-issued DOI via DataCite |
Submission history
From: Yuxin Wang [view email]
[v1]
Sat, 4 Jul 2026 13:09:33 UTC (2,188 KB)
[v2]
Tue, 7 Jul 2026 04:10:34 UTC (2,188 KB)
[v3]
Sun, 25 Oct 2026 15:55:42 UTC (2,682 KB)
来源：arXiv cs.CL · arxiv.org