Skip to content

Commit

Permalink
Update project-40-reaction_multi-agents.md
Browse files Browse the repository at this point in the history
Updated X post, members' affiliation
  • Loading branch information
bznan authored Apr 7, 2024
1 parent 65eee57 commit cac5128
Showing 1 changed file with 5 additions and 4 deletions.
9 changes: 5 additions & 4 deletions _projects/project-40-reaction_multi-agents.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,17 +3,18 @@ number: 40 # leave as-is, maintainers will adjust
title: Optimizing Chemical Reaction Conditions with Multi-Agent Systems Using Large Language Models and Bayesian Optimization
topic: general
team_leads:
- Bozhao Nan (University of Notre Dame)
- Taicheng Guo (University of Notre Dame)
- Bozhao Nan (University of Notre Dame) @bznan
- Taicheng Guo (University of Notre Dame) @taichengguo

# Comment these lines by prepending the pound symbol (#) to each line to hide these elements
contributors:
- Kehan Guo (University of Notre Dame)
- Yanqiao Zhu (UCLA)
- Kehan Guo (University of Notre Dame) @KehanGuo2
- Yanqiao Zhu (UCLA) @SXKDZ

github: AC-BO-Hackathon/project-reaction_BO_agents
youtube_video: xf6rfyUQeZQ

Check out our social media post on X: https://x.com/Bozhao95501764/status/1777029207857451508
---

This project is focused on enhancing the efficiency of the Suzuki reaction process through an advanced multi-agent system, incorporating large language models (LLMs) and Bayesian Optimization (BO). The innovation lies in the employment of specialized sub-agents, each with expertise in a crucial domain of the reaction: catalyst design, solvent effects, and base selection. These agents work in concert with a supervisory agent, which integrates their insights and findings. This collaborative framework aims to optimize reaction conditions iteratively, leveraging both prior knowledge and experimental data to navigate the chemical space effectively.
Expand Down

0 comments on commit cac5128

Please sign in to comment.