Zhewei Wei

Abstract Autonomous agents have long been a research focus in academic and industry communities. Previous research often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of Web knowledge, large language models (LLMs) have shown potential in human-level intelligence, leading to a surge in research on LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of LLM-based autonomous agents from a holistic perspective. We first discuss the construction of LLM-based autonomous agents, proposing a unified framework that encompasses much of previous work. Then, we present a overview of the diverse applications of LLM-based autonomous agents in social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field.

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the {\em over-smoothing} problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://github.com/chennnM/GCNII .

Molecular representation learning (MRL) has gained tremendous attention due to its critical role in learning from limited supervised data for applications like drug design. In most MRL methods, molecules are treated as 1D sequential tokens or 2D topology graphs, limiting their ability to incorporate 3D information for downstream tasks and, in particular, making it almost impossible for 3D geometry prediction/generation. In this paper, we propose a universal 3D MRL framework, called Uni-Mol, that significantly enlarges the representation ability and application scope of MRL schemes. Uni-Mol contains two pretrained models with the same SE(3) Transformer architecture: a molecular model pretrained by 209M molecular conformations; a pocket model pretrained by 3M candidate protein pocket data. Besides, Uni-Mol contains several finetuning strategies to apply the pretrained models to various downstream tasks. By properly incorporating 3D information, Uni-Mol outperforms SOTA in 14/15 molecular property prediction tasks. Moreover, Uni-Mol achieves superior performance in 3D spatial tasks, including protein-ligand binding pose prediction, molecular conformation generation, etc. The code, model, and data are made publicly available at https://github.com/dptech-corp/Uni-Mol.

The matching of similar pairs of objects, called similarity join, is fundamental functionality in data management. We consider the case of trajectory similarity join (TS-Join), where the objects are trajectories of vehicles moving in road networks. Thus, given two sets of trajectories and a threshold θ , the TS-Join returns all pairs of trajectories from the two sets with similarity above θ . This join targets applications such as trajectory near-duplicate detection, data cleaning, ridesharing recommendation, and traffic congestion prediction. With these applications in mind, we provide a purposeful definition of similarity. To enable efficient TS-Join processing on large sets of trajectories, we develop search space pruning techniques and take into account the parallel processing capabilities of modern processors. Specifically, we present a two-phase divide-and-conquer algorithm. For each trajectory, the algorithm first finds similar trajectories. Then it merges the results to achieve a final result. The algorithm exploits an upper bound on the spatiotemporal similarity and a heuristic scheduling strategy for search space pruning. The algorithm's per-trajectory searches are independent of each other and can be performed in parallel, and the merging has constant cost. An empirical study with real data offers insight in the performance of the algorithm and demonstrates that is capable of outperforming a well-designed baseline algorithm by an order of magnitude.

BACKGROUND: Long non-coding RNA H19 was demonstrated to be significantly correlated with tumor metastasis. However, the specific functions of H19 in colorectal cancer (CRC) metastasis and the underlying mechanism are still largely unclear. METHODS: Use public database to screen the potential lncRNA crucial for metastasis in colorectal cancer. The expression of H19 in clinical CRC specimens was detected by qRT-PCR. The effect of H19 on the metastasis of CRC cells was investigated by transwell, wound healing assays, CCK-8 assays and animal studies. The potential proteins binding to H19 were identified by LC-MS and verified by RNA immunoprecipitation (RIP). The expression of indicated RNA and proteins were measured by qRT-PCR or western blot. RESULTS: We found the expression of lncRNA H19 was significantly upregulated in primary tumor and metastatic tissues, correlated with poor prognosis in CRC. Ectopic H19 expression promoted the metastasis of colorectal cancer cells in vitro and in vivo, and induced epithelial-to-mesenchymal transition (EMT). Mechanistically, H19 directly bound to hnRNPA2B1. Knockdown of hnRNPA2B1 attenuated the H19-induce migration and invasion in CRC cells. Furthermore, H19 stabilized and upregulated the expression of Raf-1 by facilitated the interaction between hnRNPA2B1 and Raf-1 mRNA, resulting in activation of Raf-ERK signaling. CONCLUSIONS: Our findings demonstrate the role of H19/hnRNPA2B1/EMT axis in regulation CRC metastasis, suggested H19 could be a potential biomarker to predict prognosis as well as a therapeutic strategy for CRC.