Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions _gsocproposals/2026/proposal_CMS_CompOpsArchi.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ project_mentors:

Archi (AI Augmented Research Chat Intelligence) is an open-source, end-to-end framework for building AI agents to automate research and operational workflows. Various groups have already applied the system to their use case; the most advanced is the Computing Operations (CompOps) team at the Compact Muon Solenoid (CMS) experiment at CERN. CompOps has a private, constantly evolving, and scattered knowledge base, with scarce personnel on short term contracts. Archi puts together state-of-the-art, open-source tools like LangChain, knowledge graphs, and Model Context Protocol, and combines documentation, code, tickets, and live diagnostics to accurately retrieve relevant information, assisting operators in daily tasks, improving operator efficiency, and lessening the load on experts. Other groups at CMS deploying Archi for their use case include the Data Quality Monitoring (DQM) team and a group focusing on retrieval of the vast analysis code and documentation across the CMS landscape.

The goal of this GSoC project is to work on the development of autonomous agents to perform non-trivial computing operations at CMS, a task which integrates large language models with highly accurate retrieval, expert domain knowledge, heteregenous data sources, and agentic tools. The student will get familiarity with state-of-the-art and in-demand agentic tools like LangChain and MCP. like LangChain and MCP.
The goal of this GSoC project is to work on the development of autonomous agents to perform non-trivial computing operations at CMS, a task which integrates large language models with highly accurate retrieval, expert domain knowledge, heteregenous data sources, and agentic tools. The student will get familiarity with state-of-the-art and in-demand agentic tools like LangChain and MCP.


## Task idea
Expand Down Expand Up @@ -72,4 +72,4 @@ There will be a small evaluation task that we will mail to you then.

## Links

- <https://github.com/archi-physics/archi>
- <https://github.com/archi-physics/archi>