SCION让AI像科研团队一样协作，自动完成从问题到成果的全流程。
Rethinking Scientific Discovery in the Agentic Era
- 用多智能体系统构建科研流程的中枢，实现任务、工具与记忆的统一调度。
- 在材料分析、分子设计等任务中，比现有自主研究系统更擅长分解问题和复用知识。
- 适合需要长期追踪、可复现科研过程的研究者，尤其关注自动化创新链建设。
人工智能推动了科学发现，但多数AI4Science系统仍为零散工具，依赖人工协调问题定义、文献支持、模型使用、模拟、验证与知识复用。本文提出科学协作创新系统SCION（Scientific Collaborative Innovation with Agentic Organizational Nexus），作为智能体组织枢纽，通过科学代理作为元协调器，连接科研任务、工具、智能体、产物与记忆，将研究转化为可执行、可审计、可复用的操作流程。其核心为研究执行计划（REP），将高层次科学意图转化为分阶段目标、依赖关系、验证节点、工具需求、预期产物及回退条件。SCION还集成层级化多智能体执行、基于配置的专精化、选择性上下文构建、受控委派与分层认知记忆，支持长周期科研工作。我们将发现建模为靶向逆向搜索，并在有限实验预算下扩展至隐式目标场景的批量主动搜索。在材料分析、分子设计、蛋白质或抗体筛选中的应用，以及科学阅读、创意生成、分子生成与抗体筛选的实验表明，SCION优于现有自主研究智能体基线，尤其在任务分解、验证、迭代优化与记忆复用方面表现突出。总体而言，SCION推动AI从孤立工具转向可追溯、可复用的协同科研操作层。
原文摘要 · Abstract (English)
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.
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。