Agent-driven scientific experimentation is emerging across domains such as chemistry, biology, and materials, yet each tool class imposes its own execution discipline. Network experimentation requires more than one-shot topology or configuration synthesis: an experimenter must plan a task, operate a live and evolving network, interpret feedback, refine intermediate state, and validate the resulting behavior. This poster presents a Network Experimentation Harness for emulator-backed network experiments, helping LLM agents operate across these stateful workflows. The Harness pairs a semantic action interface with reusable experimentation skills to handle sequencing, timing, and verification that a careful experimenter would perform by hand. A preliminary study on GNS3-based network protocol experiments shows that this approach reduces wall-clock time by 47% and 37%, and token use by 81% and 76%, on average versus raw GNS3 access and a Python wrapper (GNS3Fy), respectively.

Compared to flat topic models, hierarchical topic models not only exploit inherent structural information in the corpus but detect better semantic topics with the help of hierarchy knowledge. Recently, Neural-Variational-Inference (NVI) based hierarchical neural topic models have achieved better performance. However, existing NVI-based models learn topics of different levels with the same strategy, i.e., word co-occurrence patterns, which causes that topics of different levels cannot be distinguished from a semantic perspective and topics of the first level degenerate into some meaningless common words. To address the above problems, we propose a novel Hierarchical Neural Topic Model with embedding cluster and neural variational inference (C-HNTM). Specifically, C-HNTM adopts Gaussian Mixture Model (GMM) to learn topics of the first level based on word embeddings, which can capture the global semantic information of the whole corpus and generate more meaningful and global semantic topics. Then, the NVI-based method is adopted to learn topics of the second level with Bag-of-Word from a document perspective, which can generate local and more detailed topics. Third, we simultaneously learn global and local topic distributions and dependency matrix by using Stochastic Gradient Variational Bayes (SGVB) estimator. Finally, we provide the detailed inference of variational lower bound and extensive experiments on three real-world datasets to validate the effectiveness of our model.

Recent years have witnessed the rapid development of heterogeneous graph neural networks (HGNNs) in information retrieval (IR) applications. Many existing HGNNs design a variety of tailor-made graph convolutions to capture structural and semantic information in heterogeneous graphs. However, existing HGNNs usually represent each node as a single vector in the multi-layer graph convolution calculation, which makes the high-level graph convolution layer fail to distinguish information from different relations and different orders, resulting in the information loss in the message passing. Then we propose a novel heterogeneous graph neural network with sequential node representation, namely Seq-HGNN. To avoid the information loss caused by the single vector node representation, we first design a sequential node representation learning mechanism to represent each node as a sequence of meta-path representations during the node message passing. Then we propose a heterogeneous representation fusion module, empowering Seq-HGNN to identify important meta-paths and aggregate their representations into a compact one. We conduct extensive experiments on four widely used datasets from Heterogeneous Graph Benchmark (HGB) and Open Graph Benchmark (OGB). Experimental results show that our proposed method outperforms state-of-the-art baselines in both accuracy and efficiency. The source code is available at https://github.com/nobrowning/SEQ_HGNN.

Accurate citation count prediction of newly published papers could help editors and readers rapidly figure out the influential papers in the future. Though many approaches are proposed to predict a paper's future citation, most ignore the dynamic heterogeneous graph structure or node importance in academic networks. To cope with this problem, we propose a Dynamic heterogeneous Graph and Node Importance network (DGNI) learning framework, which fully leverages the dynamic heterogeneous graph and node importance information to predict future citation trends of newly published papers. First, a dynamic heterogeneous network embedding module is provided to capture the dynamic evolutionary trends of the whole academic network. Then, a node importance embedding module is proposed to capture the global consistency relationship to figure out each paper's node importance. Finally, the dynamic evolutionary trend embeddings and node importance embeddings calculated above are combined to jointly predict the future citation counts of each paper, by a log-normal distribution model according to multi-faced paper node representations. Extensive experiments on two large-scale datasets demonstrate that our model significantly improves all indicators compared to the SOTA models.

Cross-lingual sentiment classification (CLSC) aims to leverage rich-labeled resources in the source language to improve prediction models of a resource-scarce domain in the target language. Existing feature representation learning-based approaches try to minimize the difference of latent features between different domains by exact alignment, which is achieved by either one-to-one topic alignment or matrix projection. Exact alignment, however, restricts the representation flexibility and further degrades the model performances on CLSC tasks if the distribution difference between two language domains is large. On the other hand, most previous studies proposed document-level models or ignored sentiment polarities of topics that might lead to insufficient learning of latent features. To solve the abovementioned problems, we propose a coarse alignment mechanism to enhance the model's representation by a group-to-group topic alignment into an aspect-level fine-grained model. First, we propose an unsupervised aspect, opinion, and sentiment unification model (AOS), which trimodels aspects, opinions, and sentiments of reviews from different domains and helps capture more accurate latent feature representation by a coarse alignment mechanism. To further boost AOS, we propose ps-AOS, a partial supervised AOS model, in which labeled source language data help minimize the difference of feature representations between two language domains with the help of logistics regression. Finally, an expectation-maximization framework with Gibbs sampling is then proposed to optimize our model. Extensive experiments on various multilingual product review data sets show that ps-AOS significantly outperforms various kinds of state-of-the-art baselines.