Sortify is the first fully autonomous LLM agent deployed in production for closed-loop recommendation ranking optimization.
March 31, 2026
Original Paper
Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange
arXiv · 2603.27765
The Takeaway
It replaces manual parameter tuning with an autonomous loop that diagnoses business outcomes and deploys new ranking parameters. It demonstrates how to successfully bridge the gap between offline proxy metrics and online business impact using LLM-based meta-control.
From the abstract
Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct.We present Sortify, the first fully autonomous LLM-driven ranking optimiza