5 papers
Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning
Wentao Zhang, Haoyu Zhang, Xinke Jiang +7
Large Language Models (LLMs) excel at multi-step reasoning, yet current parallel reasoning approaches often fail to distinguish the contributions of individual reasoning paths. Man…
SAGER: Self-Evolving User Policy Skills for Recommendation Agent
Zhen Tao, Riwei Lai, Chenyun Yu +7
Large language model (LLM) based recommendation agents personalize what they know through evolving per-user semantic memory, yet how they reason remains a universal, static system…
Task-Aware Retrieval Augmentation for Dynamic Recommendation
Zhen Tao, Xinke Jiang, Qingshuai Feng +6
Dynamic recommendation systems aim to provide personalized suggestions by modeling temporal user-item interactions across time-series behavioral data. Recent studies have leveraged…
On the Cross-type Homophily of Heterogeneous Graphs: Understanding and Unleashing
Zhen Tao, Ziyue Qiao, Chaoqi Chen +3
Homophily, the tendency of similar nodes to connect, is a fundamental phenomenon in network science and a critical factor in the performance of graph neural networks (GNNs). While…
dInfer: An Efficient Inference Framework for Diffusion Language Models
Yuxin Ma, Lun Du, Lanning Wei +20
Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallel…