3 papers
cs.IR2026
Seeing and Reflecting: Multimodal Memory-Enhanced Agent Collaboration for Recommendation
Hao Cong, Huizu Lin, Zihan Wang +3
Large language model (LLM)-based agentic recommender systems show promise in modeling user preferences through natural-language reasoning, yet they remain limited by text-centric i…
cs.LG2026
RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory
Fei Zuo, Zikang Zhou, Hao Cong +2
Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottle…
cs.CL2026
TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation
Xinkai Ma, Zhiqi Bai, Dingling Zhang +21
Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predom…