SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Yankai, Lou, Wenjie, Wang, Lilong, Tang, Zhenyu, Feng, Shiyang, Lu, Jiaxuan, Sun, Haoran, Pan, Yaning, Gu, Shuang, Su, Haoyang, Liu, Feng, Wei, Wangxu, Tan, Pan, Zhou, Dongzhan, Ling, Fenghua, Tan, Cheng, Zhang, Bo, Wang, Xiaosong, Bai, Lei, Zhou, Bowen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917177411502080
author Jiang, Yankai
Lou, Wenjie
Wang, Lilong
Tang, Zhenyu
Feng, Shiyang
Lu, Jiaxuan
Sun, Haoran
Pan, Yaning
Gu, Shuang
Su, Haoyang
Liu, Feng
Wei, Wangxu
Tan, Pan
Zhou, Dongzhan
Ling, Fenghua
Tan, Cheng
Zhang, Bo
Wang, Xiaosong
Bai, Lei
Zhou, Bowen
author_facet Jiang, Yankai
Lou, Wenjie
Wang, Lilong
Tang, Zhenyu
Feng, Shiyang
Lu, Jiaxuan
Sun, Haoran
Pan, Yaning
Gu, Shuang
Su, Haoyang
Liu, Feng
Wei, Wangxu
Tan, Pan
Zhou, Dongzhan
Ling, Fenghua
Tan, Cheng
Zhang, Bo
Wang, Xiaosong
Bai, Lei
Zhou, Bowen
contents We introduce SCP: the Science Context Protocol, an open-source standard designed to accelerate discovery by enabling a global network of autonomous scientific agents. SCP is built on two foundational pillars: (1) Unified Resource Integration: At its core, SCP provides a universal specification for describing and invoking scientific resources, spanning software tools, models, datasets, and physical instruments. This protocol-level standardization enables AI agents and applications to discover, call, and compose capabilities seamlessly across disparate platforms and institutional boundaries. (2) Orchestrated Experiment Lifecycle Management: SCP complements the protocol with a secure service architecture, which comprises a centralized SCP Hub and federated SCP Servers. This architecture manages the complete experiment lifecycle (registration, planning, execution, monitoring, and archival), enforces fine-grained authentication and authorization, and orchestrates traceable, end-to-end workflows that bridge computational and physical laboratories. Based on SCP, we have constructed a scientific discovery platform that offers researchers and agents a large-scale ecosystem of more than 1,600 tool resources. Across diverse use cases, SCP facilitates secure, large-scale collaboration between heterogeneous AI systems and human researchers while significantly reducing integration overhead and enhancing reproducibility. By standardizing scientific context and tool orchestration at the protocol level, SCP establishes essential infrastructure for scalable, multi-institution, agent-driven science.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents
Jiang, Yankai
Lou, Wenjie
Wang, Lilong
Tang, Zhenyu
Feng, Shiyang
Lu, Jiaxuan
Sun, Haoran
Pan, Yaning
Gu, Shuang
Su, Haoyang
Liu, Feng
Wei, Wangxu
Tan, Pan
Zhou, Dongzhan
Ling, Fenghua
Tan, Cheng
Zhang, Bo
Wang, Xiaosong
Bai, Lei
Zhou, Bowen
Artificial Intelligence
Multiagent Systems
We introduce SCP: the Science Context Protocol, an open-source standard designed to accelerate discovery by enabling a global network of autonomous scientific agents. SCP is built on two foundational pillars: (1) Unified Resource Integration: At its core, SCP provides a universal specification for describing and invoking scientific resources, spanning software tools, models, datasets, and physical instruments. This protocol-level standardization enables AI agents and applications to discover, call, and compose capabilities seamlessly across disparate platforms and institutional boundaries. (2) Orchestrated Experiment Lifecycle Management: SCP complements the protocol with a secure service architecture, which comprises a centralized SCP Hub and federated SCP Servers. This architecture manages the complete experiment lifecycle (registration, planning, execution, monitoring, and archival), enforces fine-grained authentication and authorization, and orchestrates traceable, end-to-end workflows that bridge computational and physical laboratories. Based on SCP, we have constructed a scientific discovery platform that offers researchers and agents a large-scale ecosystem of more than 1,600 tool resources. Across diverse use cases, SCP facilitates secure, large-scale collaboration between heterogeneous AI systems and human researchers while significantly reducing integration overhead and enhancing reproducibility. By standardizing scientific context and tool orchestration at the protocol level, SCP establishes essential infrastructure for scalable, multi-institution, agent-driven science.
title SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2512.24189