Feng Xiao

Peijie Yu, Yifan Yang, Jinjian Li et al.

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing benchmarks predominantly access agents in single-mission scenarios, failing to capture real-world complexity. To bridge this gap, we propose the Multi-Mission Tool Bench. In the benchmark, each test case comprises multiple interrelated missions. This design requires agents to dynamically adapt to evolving demands. Moreover, the proposed benchmark explores all possible mission-switching patterns within a fixed mission number. Specifically, we propose a multi-agent data generation framework to construct the benchmark. We also propose a novel method to evaluate the accuracy and efficiency of agent decisions with dynamic decision trees. Experiments on diverse open-source and closed-source LLMs reveal critical factors influencing agent robustness and provide actionable insights to the tool invocation society.

Zican Dong, Han Peng, Peiyu Liu et al.

Mixture-of-Experts (MoE) models achieve a favorable trade-off between performance and inference efficiency by activating only a subset of experts. However, the memory overhead of storing all experts remains a major limitation, especially in large-scale MoE models such as DeepSeek-R1(671B). In this study, we investigate domain specialization and expert redundancy in large-scale MoE models and uncover a consistent behavior we term few-shot expert localization, with only a few in-domain demonstrations, the model consistently activates a sparse and stable subset of experts on tasks within the same domain. Building on this observation, we propose a simple yet effective pruning framework, EASY-EP, that leverages a few domain-specific demonstrations to identify and retain only the most relevant experts. EASY-EP comprises two key components: output-aware expert importance assessment and expert-level token contribution estimation. The former evaluates the importance of each expert for the current token by considering the gating scores and L2 norm of the outputs of activated experts, while the latter assesses the contribution of tokens based on representation similarities before and after routed experts. Experiments on DeepSeek-R1 and DeepSeek-V3-0324 show that our method can achieve comparable performances and $2.99\times$ throughput under the same memory budget with full model with only half the experts.

Xiao Yan, Gang Kou, Feng Xiao et al.

Bike-sharing systems (BSSs) have become increasingly popular around the globe and have attracted a wide range of research interests. In this paper, the demand forecasting problem in BSSs is studied. Spatial and temporal features are critical for demand forecasting in BSSs, but it is challenging to extract spatiotemporal dynamics. Another challenge is to capture the relations between spatiotemporal dynamics and external factors, such as weather, day-of-week, and time-of-day. To address these challenges, we propose a multiple spatiotemporal fusion network named MSTF-Net. MSTF-Net consists of multiple spatiotemporal blocks: 3D convolutional network (3D-CNN) blocks, eidetic 3D convolutional long short-term memory networks (E3D-LSTM) blocks, and fully-connected (FC) blocks. Specifically, 3D-CNN blocks highlight extracting short-term spatiotemporal dependence in each fragment (i.e., closeness, period, and trend); E3D-LSTM blocks further extract long-term spatiotemporal dependence over all fragments; FC blocks extract nonlinear correlations of external factors. Finally, the latent representations of E3D-LSTM and FC blocks are fused to obtain the final prediction. For two real-world datasets, it is shown that MSTF-Net outperforms seven state-of-the-art models.

Feng Xiao, Dapeng Zhang, Gang Kou et al.

To collectively forecast the demand for ride-sourcing services in all regions of a city, the deep learning approaches have been applied with commendable results. However, the local statistical differences throughout the geographical layout of the city make the spatial stationarity assumption of the convolution invalid, which limits the performance of CNNs on the demand forecasting task. In this paper, we propose a novel deep learning framework called LC-ST-FCN (locally connected spatiotemporal fully-convolutional neural network) to address the unique challenges of the region-level demand forecasting problem within one end-to-end architecture (E2E). We first employ the 3D convolutional layers to fuse the spatial and temporal information existed in the input and then feed the spatiotemporal features extracted by the 3D convolutional layers to the subsequent 2D convolutional layers. Afterward, the prediction value of each region is obtained by the locally connected convolutional layers which relax the parameter sharing scheme. We evaluate the proposed model on a real dataset from a ride-sourcing service platform (DiDiChuxing) and observe significant improvements compared with a bunch of baseline models. Besides, we also illustrate the effectiveness of our proposed model by visualizing how different types of convolutional layers transform their input and capture useful features. The visualization results show that fully convolutional architecture enables the model to better localize the related regions. And the locally connected layers play an important role in dealing with the local statistical differences and activating useful regions.

Wenwen Tu, Feng Xiao, Liping Fu et al.

This study proposes a Deep Belief Network model to classify traffic flow states. The model is capable of processing massive, high-density, and noise-contaminated data sets generated from smartphone sensors. The statistical features of Vehicle acceleration, angular acceleration, and GPS speed data, recorded by smartphone software, are analyzed, and then used as input for traffic flow state classification. Data from a five-day experiment is used to train and test the proposed model. A total of 747,856 sets of data are generated and used for both traffic flow states classification and sensitivity analysis of input variables. The result shows that the proposed Deep Belief Network model is superior to traditional machine learning methods in both classification performance and computational efficiency.