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.
Network bandwidth is a scarce resource in big data environments, so data locality is a fundamental problem for data-parallel frameworks such as Hadoop and Spark. This problem is exacerbated in ...multicore server-based clusters, where multiple tasks running on the same server compete for the server’s network bandwidth. Existing approaches solve this problem by scheduling computational tasks near the input data and considering the server’s free time, data placements, and data transfer costs. However, such approaches usually set identical values for data transfer costs, even though a multicore server’s data transfer cost increases with the number of data-remote tasks. Eventually, this hampers data-processing time, by minimizing it ineffectively. As a solution, we propose DynDL (Dynamic Data Locality), a novel data-locality-aware task-scheduling model that handles dynamic data transfer costs for multicore servers. DynDL offers greater flexibility than existing approaches by using a set of non-decreasing functions to evaluate dynamic data transfer costs. We also propose online and offline algorithms (based on DynDL) that minimize data-processing time and adaptively adjust data locality. Although DynDL is NP-complete (nondeterministic polynomial-complete), we prove that the offline algorithm runs in quadratic time and generates optimal results for DynDL’s specific uses. Using a series of simulations and real-world executions, we show that our algorithms are 30% better than algorithms that do not consider dynamic data transfer costs in terms of data-processing time. Moreover, they can adaptively adjust data localities based on the server’s free time, data placement, and network bandwidth, and schedule tens of thousands of tasks within subseconds or seconds.
Abstract
At present, the research of object detection in automatic driving is mainly based on the actual automatic driving vehicle. This method is expensive, less feasible, and difficult to test. ...Based on CARLA, we proposed an efficient and low-cost object detection method, which can overcome the shortcomings of the actual vehicle research. In this paper, firstly, we obtained images from CARLA, and then the data set is obtained by cleaning and labeling the image. Finally, based on the data set established in this paper, we train the models of YOLOv4, CenterNet and Faster-RCNN respectively, and make a comparative study on the test set. The results show that YOLOv4 has the best detection effect without special optimization method.
Purpose
Soil aggregates are the basic unit of soil structure and have a significant impact on soil organic carbon (SOC) sequestration. Most of the current research focuses on the effect of vegetation ...restoration on soil organic carbon storage, while the response of soil organic carbon stability and influencing factors under different vegetation restoration modes is still unclear.
Methods
This study uses stable carbon isotopes and Fourier transform infrared spectroscopy to characterize soil organic carbon compounds, and elucidate the effects of natural shrub (NS), natural grassland (NG), olive grove (OG), and cropland (CL) restoration on soil organic carbon stability.
Results
The results showed that the proportion of macroaggregates in the topsoil of cropland was about 1.5 times that of other vegetation types during the same restoration period. However, the content of organic carbon in the macroaggregates is not the most, indicating that the macroaggregates are not conducive to maintain the stability of organic carbon. The content of stable organic carbon in natural grassland soil was the highest, and the accumulation of soil organic carbon was the highest.
Conclusions
We considered natural grassland soil has the greatest carbon sequestration potential. The content of unstable polysaccharides in olive groves was the highest about 75%, which made organic carbon easily decomposed, resulting in the least accumulation of olive groves. The findings are directly relevant to regional policies to promote vegetation restoration, and natural revegetation can help restore ecosystem function in vulnerable areas.
On October 3, 2021, a large landslide occurred at the loess-mudstone interface in Nandianzi, Lingtai, its successful early warning measures preventing casualties. In order to investigate the ...occurrence mechanism behind the Nandianzi landslide, a basic investigation was conducted, covering the topography, lithology, hydrogeological conditions, and human engineering activities related to the landslide. Based on the characteristics and differences of the crack development of the landslide, the landslide mass was divided into five blocks. The characteristics of each block were thoroughly analyzed through qualitative and quantitative analysis. The specific sliding situation of different parts of the landslide was analyzed, and further evidence was provided for the objective rationality of landslide classification and zoning, as well as the analysis of landslide mechanisms. Ultimately, it is concluded that the main causes of landslide disasters are as follows: (1) Large-scale excavation and earthwork activities at
Cross-Domain Recommendation (CDR) is an effective way to alleviate the cold-start problem. However, previous work severely ignores fairness and bias when learning the mapping function, which is used ...to obtain the representations for fresh users in the target domain. To study this problem, in this paper, we propose a Fairness-aware Cross-Domain Recommendation model, called FairCDR. Our method achieves user-oriented group fairness by learning the fairness-aware mapping function. Since the overlapping data are quite limited and distributionally biased, FairCDR leverages abundant non-overlapping users and interactions to help alleviate these problems. Considering that each individual has different influence on model fairness, we propose a new reweighing method based on Influence Function (IF) to reduce unfairness while maintaining recommendation accuracy. Extensive experiments are conducted to demonstrate the effectiveness of our model.
Fairness in the recommendation domain has recently attracted increasing attention due to more and more concerns about the algorithm discrimination and ethics. While recent years have witnessed many ...promising fairness aware recommender models, an important problem has been largely ignored, that is, the fairness can be biased due to the user personalized selection tendencies or the non-uniform item exposure probabilities. To study this problem, in this paper, we formally define a novel task named as unbiased fairness aware Top-N recommendation. For solving this task, we firstly define an ideal loss function based on all the user-item pairs. Considering that, in real-world datasets, only a small number of user-item interactions can be observed, we then approximate the above ideal loss with a more tractable objective based on the inverse propensity score (IPS). Since the recommendation datasets can be noisy and quite sparse, which brings difficulties for accurately estimating the IPS, we propose to optimize the objective in an IPS range instead of a specific point, which improves the model fault tolerance capability. In order to make our model more applicable to the commonly studied Top-N recommendation, we soften the ranking metrics such as Precision, Hit-Ratio, and NDCG to derive a fully differentiable framework. We conduct extensive experiments to demonstrate the effectiveness of our model based on four real-world datasets.
In order to support the study of recent advances in recommender systems, this paper presents an extended recommendation library consisting of eight packages for up-to-date topics and architectures. ...First of all, from a data perspective, we consider three important topics related to data issues (ie sparsity, bias and distribution shift ), and develop five packages accordingly, including meta-learning, data augmentation, debiasing, fairness and cross-domain recommendation. Furthermore, from a model perspective, we develop two benchmarking packages for Transformer-based and graph neural network~(GNN)-based models, respectively. All the packages (consisting of 65 new models) are developed based on a popular recommendation framework RecBole, ensuring that both the implementation and interface are unified. For each package, we provide complete implementations from data loading, experimental setup, evaluation and algorithm implementation. This library provides a valuable resource to facilitate the up-to-date research in recommender systems. The project is released at the link: \urlhttps://github.com/RUCAIBox/RecBole2.0.
Uplift modeling has shown very promising results in online marketing. However, most existing works are prone to the robustness challenge in some practical applications. In this paper, we first ...present a possible explanation for the above phenomenon. We verify that there is a feature sensitivity problem in online marketing using different real-world datasets, where the perturbation of some key features will seriously affect the performance of the uplift model and even cause the opposite trend. To solve the above problem, we propose a novel robustness-enhanced uplift modeling framework with adversarial feature desensitization (RUAD). Specifically, our RUAD can more effectively alleviate the feature sensitivity of the uplift model through two customized modules, including a feature selection module with joint multi-label modeling to identify a key subset from the input features and an adversarial feature desensitization module using adversarial training and soft interpolation operations to enhance the robustness of the model against this selected subset of features. Finally, we conduct extensive experiments on a public dataset and a real product dataset to verify the effectiveness of our RUAD in online marketing. In addition, we also demonstrate the robustness of our RUAD to the feature sensitivity, as well as the compatibility with different uplift models.
Uplift modeling has shown very promising results in online marketing. However, most existing works are prone to the robustness challenge in some practical applications. In this paper, we first ...present a possible explanation for the above phenomenon. We verify that there is a feature sensitivity problem in online marketing using different real-world datasets, where the perturbation of some key features will seriously affect the performance of the uplift model and even cause the opposite trend. To solve the above problem, we propose a novel robustness-enhanced uplift modeling framework with adversarial feature desensitization (RUAD). Specifically, our RUAD can more effectively alleviate the feature sensitivity of the uplift model through two customized modules, including a feature selection module with joint multi-label modeling to identify a key subset from the input features and an adversarial feature desensitization module using adversarial training and soft interpolation operations to enhance the robustness of the model against this selected subset of features. Finally, we conduct extensive experiments on a public dataset and a real product dataset to verify the effectiveness of our RUAD in online marketing. In addition, we also demonstrate the robustness of our RUAD to the feature sensitivity, as well as the compatibility with different uplift models.
PDF
