5 papers
Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents
Emmanuel Aboah Boateng, Kyle MacDonald, Amardeep Kumar +2
Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency, and generat…
Joint Optimization of Relevance and Engagement in Multi-Task Ranking for E-Commerce with Efficient LLM Supervision
Luming Chen, Jiaqi Xi, Raghav Saboo +7
Optimizing industrial search ranking models solely for user engagement signals often introduces systematic biases, prioritizing popular or price-anchored items that may not satisfy…
Agentic Multi-Source Grounding for Enhanced Query Intent Understanding: A DoorDash Case Study
Emmanuel Aboah Boateng, Kyle MacDonald, Akshad Viswanathan +1
Accurately mapping user queries to business categories is a fundamental Information Retrieval challenge for multi-category marketplaces, where context-sparse queries such as "Wildf…
Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
Alejandro Breen Herrera, Aayush Sheth, Steven G. Xu +8
Conversational shopping assistants (CSAs) represent a compelling application of agentic AI, but moving from prototype to production reveals two underexplored challenges: how to eva…
Mine and Refine: Optimizing Graded Relevance in E-commerce Search Retrieval
Jiaqi Xi, Raghav Saboo, Luming Chen +2
We propose a two-stage "Mine and Refine" contrastive training framework for semantic text embeddings to enhance multi-category e-commerce search retrieval. Large scale e-commerce s…