Zhiwei Liu

Cheng Qian, Zuxin Liu, Akshara Prabhakar et al. · princeton

Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value of such agents lies in their ability to assist users, a setting where diversity and dynamics of user interaction pose challenges. In this work, we propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments paired with simulated users. We systematically vary turn-level reward assignment and trajectory-level score calculation to analyze how different formulations affect learning under the GRPO algorithm. Our experiments across Qwen3 models reveal three key findings: (i) SFT cold start is critical for unlocking initial interaction ability and enabling sustained RL improvements; (ii) deliberate trajectory scoring yields more efficient and effective multi-turn interactions; and (iii) while stronger simulated users (e.g., GPT-4o) facilitates training, open-source simulators (e.g., Qwen3-32B) remain a cost-effective and transferable option. Together, these results highlight that careful design of reward shaping and user simulation choice is as crucial as model scale, and establish UserRL as a practical pathway for developing robust user-centric agentic models. All codes and data are public for future research.

Zhiwei Liu, Lin Meng, Fei Jiang et al.

Collaborative Filtering (CF) signals are crucial for a Recommender System~(RS) model to learn user and item embeddings. High-order information can alleviate the cold-start issue of CF-based methods, which is modelled through propagating the information over the user-item bipartite graph. Recent Graph Neural Networks~(GNNs) propose to stack multiple aggregation layers to propagate high-order signals. However, the oscillation problem, varying locality of bipartite graph, and the fix propagation pattern spoil the ability of multi-layer structure to propagate information. The oscillation problem results from the bipartite structure, as the information from users only propagates to items. Besides oscillation problem, varying locality suggests the density of nodes should be considered in the propagation process. Moreover, the layer-fixed propagation pattern introduces redundant information between layers. In order to tackle these problems, we propose a new RS model, named as \textbf{D}eoscillated \textbf{G}raph \textbf{C}ollaborative \textbf{F}iltering~(DGCF). We introduce cross-hop propagation layers in it to break the bipartite propagating structure, thus resolving the oscillation problem. Additionally, we design innovative locality-adaptive layers which adaptively propagate information. Stacking multiple cross-hop propagation layers and locality layers constitutes the DGCF model, which models high-order CF signals adaptively to the locality of nodes and layers. Extensive experiments on real-world datasets show the effectiveness of DGCF. Detailed analyses indicate that DGCF solves oscillation problem, adaptively learns local factor, and has layer-wise propagation pattern. Our code is available online at https://github.com/JimLiu96/DeosciRec.

Cheng Qian, Zuxin Liu, Shirley Kokane et al. · princeton

Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle on complex tasks. Static escalation rules and keyword heuristics under-utilize this spectrum and fail to adapt across task types. We present xRouter, a tool-calling-based routing system in which a learned router can either answer directly or invoke one or more external models. The router is trained end-to-end with reinforcement learning using an explicit, cost-aware reward that encodes cost-performance trade-offs, eliminating the need for hand-engineered routing rules. Our implementation encompasses the full reinforcement learning framework, including reward and cost accounting, as well as the deployment and evaluation pipelines. Across diverse benchmarks, xRouter achieves strong cost-performance trade-offs (e.g., substantial cost reductions at comparable task completion rates), and provides empirical insights into what reliably helps learned routing and what does not, ranging from model trainability to the difficulty of eliciting sophisticated orchestration behaviors in small open models. We hope these findings and our open implementation will serve as a practical substrate for advancing learned, cost-aware LLM orchestration.

Xiaolin Yan, Yangxing Liu, Jiazhang Zheng et al.

Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically developed for the semiconductor display industry. This model is designed to deliver expert-level understanding and reasoning for the industry's complex challenges. Leveraging a carefully curated industry knowledge base, the model undergoes supervised fine-tuning and reinforcement learning to enhance its reasoning and comprehension capabilities. To further accelerate development, we implemented an automated evaluation framework that simulates expert-level assessments. We also integrated a domain-specific retrieval-augmented generation (RAG) mechanism, resulting in notable performance gains on benchmark datasets. Despite its relatively compact size of 32 billion parameters, X-Intelligence 3.0 outperforms SOTA DeepSeek-R1-671B across multiple evaluations. This demonstrates its exceptional efficiency and establishes it as a powerful solution to the longstanding reasoning challenges faced by the semiconductor display industry.