# MIT-Led Team Receives Funding to Develop Next-Generation Weed Killers Researchers utilize generative AI to create safer, effective alternatives to traditional chemical herbicides. - **Source:** [MIT News — AI](https://news.mit.edu/topic/artificial-intelligence2) - **Published:** 2026-11-10 - **Topic:** [science](https://brifing.si/c/science) - **Original article:** - **On Brifing:** https://brifing.si/s/18adb931-f564-4a37-b346-2ec2e723c170 ## New Agricultural Research Initiative MIT researchers are leading a 53 million dollar project funded by ARPA-H under the STREAM program. This initiative aims to develop next-generation weed killers that prioritize human health while maintaining agricultural productivity. The project addresses the urgent need for alternatives to common herbicides like glyphosate, which face increasing resistance issues. ## The Challenge of Resistance Over 1 billion pounds of herbicide are applied annually in the United States. However, weeds are developing genetic mutations that render current chemicals less effective. This resistance threatens crop yields and economic stability, while simultaneously raising concerns regarding the national security of the supply chain for essential agricultural chemical precursors. ## Health and Environmental Risks Frequent herbicide use poses potential risks for cancer, metabolic disorders, and endocrine issues among farm workers. Furthermore, residues often reach the general population through food and drinking water supplies. Developing safer alternatives is critical to reducing environmental damage and minimizing human exposure to these potentially harmful chemical compounds globally. ## Generative AI for Discovery The PLOW project utilizes generative AI models to predict molecules that disrupt plant enzymes targeted by existing herbicides. Led by Connor Coley, Regina Barzilay, and Alexander Tropsha, the team aims to identify candidates that effectively kill weeds while ensuring low toxicity for humans and minimal ecological impact during agricultural use. ## High-Throughput Screening Process After AI models generate billions of potential candidates, a dedicated team led by Angela Koehler and Jaime Cheah will perform high-throughput screening. This process identifies molecules that successfully hit their targets. The resulting data is fed back into the computational models, creating a continuous loop that improves the accuracy of future predictions. ## Greenhouse Testing and Validation Following initial screening, researchers from institutions including the University of Tennessee and the University of Illinois will conduct greenhouse studies. These tests evaluate molecule performance under diverse agricultural conditions. The team expects to complete the first greenhouse tests of initial RNAi candidates by the end of the program's first year. ## Innovative Microbial Degradation The project also focuses on developing living microbial systems to degrade agrochemicals before they contaminate food, soil, or waterways. Engineered bacteria, fungi, and RNAi will convert these chemicals into biomass. This scalable strategy provides a secondary layer of protection, significantly reducing environmental and human exposure to hazardous agricultural chemical residues. ## Strategic Agricultural Impact By reducing dependency on imported phosphorus and glyphosate, this research seeks to secure the future of U.S. crop yields. The integration of synthetic biology and AI represents a shift toward more sustainable farming practices. These advancements are essential for maintaining affordable food prices while addressing the growing crisis of herbicide resistance. ## Sources covering this story - https://news.mit.edu/2026/mit-led-team-receives-funding-next-generation-alternatives-modern-weed-killers-1110 — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._