AI Co-Scientist for Ranking: Discovering Novel Search Ranking Models alongside LLM-based AI Agents with Cloud Computing Access

TL;DR

This paper introduces an AI Co-Scientist framework that automates the entire search ranking research process, discovering novel models and techniques with minimal human intervention, leveraging multiple LLMs and cloud computing.

Contribution

The study presents the first application of an AI Co-Scientist framework in ranking research, automating idea generation, implementation, and training, leading to novel ranking models.

Findings

Discovered a new technique for sequence feature handling.

Automated model enhancements improved offline performance.

AI systems can match human-level ranking architecture discovery.

Abstract

Recent advances in AI agents for software engineering and scientific discovery have demonstrated remarkable capabilities, yet their application to developing novel ranking models in commercial search engines remains unexplored. In this paper, we present an AI Co-Scientist framework that automates the full search ranking research pipeline: from idea generation to code implementation and GPU training job scheduling with expert in the loop. Our approach strategically employs single-LLM agents for routine tasks while leveraging multi-LLM consensus agents (GPT 5.2, Gemini Pro 3, and Claude Opus 4.5) for challenging phases such as results analysis and idea generation. To our knowledge, this is the first study in the ranking community to utilize an AI Co-Scientist framework for algorithmic research. We demonstrate that this framework discovered a novel technique for handling sequence features, with all model enhancements produced automatically, yielding substantial offline performance improvements. Our findings suggest that AI systems can discover ranking architectures comparable to those developed by human experts while significantly reducing routine research workloads.