Weco AI Team Demonstrates AutoResearch Parameter Golf Workshop
Weco AI released a video featuring Zhengyao Jiang, Dixing Xu, and others introducing their Aiden system and Mini Parameter Golf tool. The content covers automated research loops, evaluation stability, and experiment tree visualization, suitable for engineers focused on AI automation workflows.
ImportanceLocalEvidenceE2 unreplicatedWrite-upQuick
Weco AI published a video on October 11, 2026, titled "Parameter Golf with AutoResearch." Presented by Vayum Arora, Zhengyao Jiang, Dixing Xu, and Dhruv Srikanth, the resource introduces how to transform code improvement loops in language model training into inspectable small-scale experiments.
In the video, Zhengyao Jiang introduces autoresearch as repeated proposals and evaluations, while Dixing Xu explains the team's Aiden system and its contributions to OpenAI's Parameter Golf challenge. Vayum Arora and Dhruv Srikanth then demonstrate a practical setup combining a modifiable source file, a fixed evaluation command, and a measurable goal.
For AI engineers and researchers interested in designing fast and stable evaluations, preventing reward hacking, and steering search directions via experiment trees, this video offers specific operational perspectives and tool context.