Parameter Golf with AutoResearch — Vayum Arora, Zhengyao Jiang, Dixing Xu & Dhruv Srikanth, Weco AI
Weco AI's AutoResearch agent won OpenAI's Prompt Golf competition in April
“Auto Research is essentially a cycle of trial and error. You provide the language model with your code and a script for evaluation, which can be repeated.”
Weco AI presented a workshop on AutoResearch, an agentic loop that iteratively tries and evaluates code changes to optimize metrics like accuracy, speed, and cost. Their research agent Aiden won OpenAI's Prompt Golf competition in April, and the technique has seen real production adoption including reducing latency in Shopify's CI/CD pipeline. The content is primarily a workshop introduction rather than a major announcement, limiting its newsletter signal value.