21 papers
Empowering Compact LLMs with Fusion of Layer-wise Exits for Recommendation
Xurong Liang, Tong Chen, Quoc Viet Hung Nguyen +3
Large language model-based recommender systems (LLM-RSs) have demonstrated remarkable capabilities, but are computationally unsustainable for many real-world applications. Compact…
ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning
Jiaqi Zhang, Tong Chen, Junliang Yu +2
Agentic systems have rapidly advanced in their ability to interact with real-world environments, leverage external tools, and provide services for users. However, unlike natural-wo…
VaLiDRec: Variable-Length LLM-Aligned Semantic IDs for Generative Recommendation
Shutong Qiao, Wei Yuan, Tong Chen +3
Generative recommendation commonly represents items using fixed-length semantic identifiers (SIDs) constructed through clustering and quantization. However, these artificial codes…
Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering
Rezarta Islamaj, Joey Chan, Robert Leaman +13
Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple sources to answer complex que…
GRAFT: Graph-Tokenized LLMs for Tool Planning
Xinyi Gao, Xinyu Ren, Junliang Yu +3
Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This requires aligning tool choices…
Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems
Zongwei Wang, Min Gao, Hongzhi Yin +5
Large language model-empowered agentic recommender systems (ARS) reformulate recommendation as a multi-turn interaction between a recommender agent and a user agent, enabling itera…