With the rapid growth of technology, especially the widespread application of artificial intelligence (AI) technology, the risk management level of commercial banks is constantly reaching new heights. In the current wave of digitalization, AI has become a key driving force for the strategic transformation of financial institutions, especially the banking industry. For commercial banks, the stability and safety of asset quality are crucial, which directly relates to the long-term stable growth of the bank. Among them, credit risk management is particularly core because it involves the flow of a large amount of funds and the accuracy of credit decisions. Therefore, establishing a scientific and effective credit risk decision-making mechanism is of great strategic significance for commercial banks. In this context, the innovative application of AI technology has brought revolutionary changes to bank credit risk management. Through deep learning and big data analysis, AI can accurately evaluate the credit status of borrowers, timely identify potential risks, and provide banks with more accurate and comprehensive credit decision support. At the same time, AI can also achieve realtime monitoring and early warning, helping banks intervene before risks occur and reduce losses.

For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that can adapt to diverse scenarios. Due to the versatile capabilities they demonstrate, large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI), offering hope for building general AI agents. Many researchers have leveraged LLMs as the foundation to build AI agents and have achieved significant progress. In this paper, we perform a comprehensive survey on LLM-based agents. We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. Building upon this, we present a general framework for LLM-based agents, comprising three main components: brain, perception, and action, and the framework can be tailored for different applications. Subsequently, we explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation. Following this, we delve into agent societies, exploring the behavior and personality of LLM-based agents, the social phenomena that emerge from an agent society, and the insights they offer for human society. Finally, we discuss several key topics and open problems within the field. A repository for the related papers at https://github.com/WooooDyy/LLM-Agent-Paper-List.

Generative AI is a fascinating field that has gained a lot of attention in recent years. It involves using machine learning algorithms to generate new data based on existing data. This technology has the potential to transform a wide range of industries, including healthcare, finance, and entertainment. In this article, we will explore what generative AI is, how it is being used today, and what the future holds for this exciting field. Generative AI is a subset of artificial intelligence (AI) that involves using algorithms to create new data.

Reinforcement Learning (RL) is a type of machine learning that focuses on training agents to make decisions in an environment by maximizing a reward signal. It differs from supervised learning, where the agent is given a labeled dataset to learn from, and unsupervised learning, where the agent is given an unlabeled dataset to find patterns on its own. In RL, the agent learns by interacting with the environment and receiving feedback in the form of rewards or penalties. One of the most popular applications of RL is in the field of gaming. RL algorithms have been used to train agents to play a wide range of games, from simple arcade games to complex strategy games such as Go and chess.

Artificial intelligence is transforming how businesses across many different industries operate. The McKinsey Technology Trends Outlook 2022 report took an in-depth look at AI and its many applications - which reach far beyond the tech industry. Here's a look at a few major sectors where AI will have important impacts. AI has the potential to optimize the agricultural sector by enabling precision agriculture and automating some functions. Precision agriculture refers to the tailoring of crop inputs to the precise needs of the farm.

Today, most of the large-scale conversational AI agents such as Alexa, Siri, or Google Assistant are built using manually annotated data to train the different components of the system including automatic speech recognition (ASR), natural language understanding (NLU), and entity resolution (ER). Typically, the accuracy of the machine learning models in these components are improved by manually transcribing and annotating data. As the scope of these systems increase to cover more scenarios and domains, manual annotation to improve the accuracy of these components becomes prohibitively costly and time con-suming. In this paper, we propose a system that leverages customer/system interaction feedback signals to automate learning without any manual annotation. Users of these systems tend to modify a previous query in hopes of fixing an error in the previous turn to get the right results.

Competitive analysis is a critical part of any business. Product managers, sellers, and marketers spend time and resources scouring through an immense amount of online and offline content, aiming to discover what their competitors are doing in the marketplace to understand what type of threat they pose to their business' financial well-being. Currently, this process is time and labor-intensive, slow and costly. This paper presents Clarity, a data-driven unsupervised system for assessment of products, which is currently in deployment in the global technology company, IBM. Clarity has been running for more than a year and is used by over 4,500 people to perform over 200 competitive analyses involving over 1000 products.

Knowledge graphs have been around for almost half a century – as the term was first coined in 1972! For a long time, they simply languished in the academic world until Google announced their knowledge graph in 2012. Since then, knowledge graphs have evolved quite dramatically, and now there is no turning back. The last 10 years have seen a meteoric rise in machine learning (ML) and artificial intelligence (AI). Because of their ability to drive intelligence into data and add context, knowledge graphs are used to make ML and AI more reliable, robust, trustworthy, and explainable.

How machine learning and AI are being used to cut emissions, picture the past, and study DNA. This company claims their AI platform can cut carbon dioxide emissions by improving buildings' efficiency. Read how an artist used machine learning to extrapolate realistic portraits of ancient Roman emperors. Researchers at the University of California San Diego have used machine learning to solve a long-standing question about gene activation in humans.

Real-time traffic signal control presents a challenging multiagent planning problem, particularly in urban road networks where, unlike simpler arterial settings, there are competing dominant traffic flows that shift through the day. Further complicating matters, urban environments require attention to multimodal traffic flows (vehicles, pedestrians, bicyclists, buses) that move at different speeds and may be given different priorities. For the past several years, my research group has been developing and refining a real-time, adaptive traffic signal control system to address these challenges, referred to as scalable urban traffic control (Surtrac). Combining principles from automated planning and scheduling, multiagent systems, and traffic theory, Surtrac treats traffic signal control as a decentralized online planning process. In operation, each intersection repeatedly generates and executes (in rolling horizon fashion) signal-timing plans that optimize the movement of currently sensed approaching traffic through the intersection.