Matrices - Training Environments for LLM Agents

Training environments for multimodal LLM-based agents on realistic computer use tasks.

Since March, we've partnered with frontier AI labs to help train computer use agents in the vein of ChatGPT Agent. Along the way, we've realized that no more surprising research breakthroughs are needed to automate most of the work that humans do today. The bottleneck is now engineering. But there's a lot of it to do. For most of LLM history, progress has been made primarily from scaling up SFT, which is about learning to mimic humans directly from records of human behavior. But over the last couple of years, the most exciting progress in AI capabilities has been through RL, which is about…

related reading

• A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
• LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
• The Era of Experience Paper.pdfstorage.googleapis.com
• Building Effective AI Agents \ Anthropicanthropic.com
• The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
• RL Environments and RL for Science: Data Foundries and Multi-Agent Architecturesnewsletter.semianalysis.com
• 2025 LLM Year in Review – karpathykarpathy.bearblog.dev
• Building Effective AI Agents \ Anthropicanthropic.com
• Sporks of AGIsergeylevine.substack.com
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Trust me bro, just one more RL scale up, this one will be the real scale up with the good environments, the actually legit one, trust me bro — AI Alignment Forumalignmentforum.org
• Language Models can Solve Computer Tasksarxiv.org