Publications (9)
PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation
Lianshang Cai, Linhao Zhang, Dehong Ma +6
Pre-trained language models have become a crucial part of ranking systems and achieved very impressive effects recently. To maintain high performance while keeping efficient comput…
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
Jiayin Zhu, Kelong Mao, Yudong Guo +4
Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, ove…
MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification
Yiqun Chen, Jiaxin Mao, Yi Zhang +7
Search result diversification (SRD), which aims to ensure that documents in a ranking list cover a broad range of subtopics, is a significant and widely studied problem in Informat…
ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons
Adrian Li, Kelong Mao, Yudong Guo +7
Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product. Such combo-shopping tasks arise in device setup, meal prepa…
CPS-MEBR: Click Feedback-Aware Web Page Summarization for Multi-Embedding-Based Retrieval
Wenbiao Li, Pan Tang, Zhengfan Wu +7
Embedding-based retrieval (EBR) is a technique to use embeddings to represent query and document, and then convert the retrieval problem into a nearest neighbor search problem in t…
Learning from Online User Feedback for Shopping Agents
Haobo Zhang, Kelong Mao, Sulong Xu +2
Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable s…