5 papers
No-Human in the Loop: Agentic Evaluation at Scale for Recommendation
Tao Zhang, Kehui Yao, Luyi Ma +7
Evaluating large language models (LLMs) as judges is increasingly critical for building scalable and trustworthy evaluation pipelines. We present ScalingEval, a large-scale benchma…
MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
Shreeranjani Srirangamsridharan, Ali Abavisani, Reza Yousefi Maragheh +4
Meta titles and descriptions strongly shape engagement in search and recommendation platforms, yet optimizing them remains challenging. Search engine ranking models are black box e…
GRACE: Generative Recommendation via Journey-Aware Sparse Attention on Chain-of-Thought Tokenization
Luyi Ma, Wanjia Zhang, Kai Zhao +15
Generative models have recently demonstrated strong potential in multi-behavior recommendation systems, leveraging the expressive power of transformers and tokenization to generate…
ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
Reza Yousefi Maragheh, Pratheek Vadla, Priyank Gupta +7
Retrieval-Augmented Generation (RAG) has shown promise in enhancing recommendation systems by incorporating external context into large language model prompts. However, existing RA…
Scalable Permutation-Aware Modeling for Temporal Set Prediction
Ashish Ranjan, Ayush Agarwal, Shalin Barot +1
Temporal set prediction involves forecasting the elements that will appear in the next set, given a sequence of prior sets, each containing a variable number of elements. Existing…