8 papers
Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation
Shijun Li, Yang Liu, Najmeh Sadoughi +5
Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology. However, exis…
Counterfactual Self-Evolving Agents for Evidence-Grounded Reasoning
Xing Han, Yuxin Wang, Chen Chen +8
Self-play proposer--solver methods improve reasoning by generating tasks and learning from verified solutions. However, for evidence-identifiable tasks, where case-specific evidenc…
MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling
Hsing-Huan Chung, Shijun Li, Yoav Wald +3
Multimodal irregular time series (MITS) consist of asynchronous and irregularly sampled observations from heterogeneous numerical and textual channels. In healthcare, for example,…
Goal-Conditioned Supervised Learning for LLM Fine-Tuning
Shijun Li, Kaiwen Dong, Xiang Gao +1
Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline para…
RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
Shijun Li, Wooseong Yang, Pranav Belligundu +3
Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and natural-language reasoning abi…
LLM Reasoning for Cold-Start Item Recommendation
Shijun Li, Yu Wang, Jin Wang +3
Large Language Models (LLMs) have shown significant potential for improving recommendation systems through their inherent reasoning capabilities and extensive knowledge base. Yet,…
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
Shijun Li, Hilaf Hasson, Joydeep Ghosh
Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein…
Goal-Conditioned Supervised Learning for Multi-Objective Recommendation
Shijun Li, Hilaf Hasson, Jing Hu +1
Multi-objective learning endeavors to concurrently optimize multiple objectives using a single model, aiming to achieve high and balanced performance across diverse objectives. How…