In this brief note, we considers the problem of learning with dynamic-optimizing principal-agent setting, in which the agents are allowed to have global perspectives about the learning process, i.e., the ability to view things according to their relative importances or in their true relations based-on some aggregated information shared by the principal. Whereas, the principal, which is exerting an influence on the learning process of the agents in the aggregation, is primarily tasked to solve a high-level optimization problem posed as an empirical-likelihood estimator under conditional moment restrictions model that also accounts information about the agents' predictive performances on out-of-samples as well as a set of private datasets available only to the principal (e.g., see [1], [2], [3], [4] and [5] for further discussions on empirical likelihood methods with moment restrictions). Here, we provide a coherent mathematical argument which is necessary for characterizing the learning process behind this abstract dynamic-optimizing principal-agent learning framework. Note that, due to the inherent feedbacks behavior among the agents, the proposed learning framework remarkably offers some advantages in terms of stability and consistency, despite that both the principal and the agents do not necessarily need to have any knowledge of the sample distributions or the quality of each others datasets. Finally, it is worth remarking that such a learning framework can provide new insights in the context of collaborative learning problem with global perspectives that exploits the principal-agent setting (e.g., see [6], [7], [8] or [9] for related discussions), although we acknowledge that there are a number of conceptual and theoretical problems, such as small sample properties, still need to be addressed.

This systematic literature review examines the role of machine learning in fraud detection within digital banking, synthesizing evidence from 118 peer-reviewed studies and institutional reports. Following the PRISMA guidelines, the review applied a structured identification, screening, eligibility, and inclusion process to ensure methodological rigor and transparency. The findings reveal that supervised learning methods, such as decision trees, logistic regression, and support vector machines, remain the dominant paradigm due to their interpretability and established performance, while unsupervised anomaly detection approaches are increasingly adopted to address novel fraud patterns in highly imbalanced datasets. Deep learning architectures, particularly recurrent and convolutional neural networks, have emerged as transformative tools capable of modeling sequential transaction data and detecting complex fraud typologies, though challenges of interpretability and real-time deployment persist. Hybrid models that combine supervised, unsupervised, and deep learning strategies demonstrate superior adaptability and detection accuracy, highlighting their potential as convergent solutions.

Currently, prompting techniques can be mainly divided into two categories:1)shot method implicitly inspires the model to answer the question by mimicing the steps in the given example, e.g., the few-shot CoT. 2) Guideline method explicitly instructs the model to reason by following guidelines, which contains succinct and concise task-specific knowledge. Shot method is prone to difficulties in terms of selection of shots type, the number of shots, and the design of the reasoning steps, so a question arises: can we only use guideline instead of shot in the prompt? To this end, we propose the FGT framework to automatically learn task-specific guidelines from dataset consisting of Feedback, Guideline, and Tree-gather agents. First, the feedback agent is designed to evaluate the outcomes, both right and wrong, of each Q&A to gather insights guiding more effective optimization strategies. Next, the guideline agent is tasked with deriving guidelines from each piece of feedback and storing them in local memory. Lastly, the tree-gather agent aggregates all guidelines hierarchically through a tree structure, ultimately obtaining all unduplicated guidelines from a global perspective. In addition, we induce the model to generate intermediate processes to ensure the reasoning consistent with the guidelines. Experimental results demonstrate that our approach achieves superior performance across multiple tasks, thereby highlighting the effectiveness of using the guidelines in prompt.

Representation learning on text-attributed graphs (TAGs) is vital for real-world applications, as they combine semantic textual and contextual structural information. Research in this field generally consist of two main perspectives: local-level encoding and global-level aggregating, respectively refer to textual node information unification (e.g., using Language Models) and structure-augmented modeling (e.g., using Graph Neural Networks). Most existing works focus on combining different information levels but overlook the interconnections, i.e., the contextual textual information among nodes, which provides semantic insights to bridge local and global levels. In this paper, we propose GraphBridge, a multi-granularity integration framework that bridges local and global perspectives by leveraging contextual textual information, enhancing fine-grained understanding of TAGs. Besides, to tackle scalability and efficiency challenges, we introduce a graphaware token reduction module. Extensive experiments across various models and datasets show that our method achieves state-of-theart performance, while our graph-aware token reduction module significantly enhances efficiency and solves scalability issues.

Exploration systems are critical for enhancing the autonomy of robots. Due to the unpredictability of the future planning space, existing methods either adopt an inefficient greedy strategy or require a lot of resources to obtain a global solution. In this work, we address the challenge of obtaining global exploration routes with minimal computing resources. A hierarchical planning framework dynamically divides the planning space into subregions and arranges their orders to provide global guidance for exploration. Indicators that are compatible with the subregion order are used to choose specific exploration targets, thereby considering estimates of spatial structure and extending the planning space to unknown regions. Extensive simulations and field tests demonstrate the efficacy of our method in comparison to existing 2D LiDAR-based approaches. Our code has been made public for further investigation.

In this report, we investigate (element-based) inconsistency measures for multisets of business rule bases. Currently, related works allow to assess individual rule bases, however, as companies might encounter thousands of such instances daily, studying not only individual rule bases separately, but rather also their interrelations becomes necessary, especially in regard to determining suitable re-modelling strategies. We therefore present an approach to induce multiset-measures from arbitrary (traditional) inconsistency measures, propose new rationality postulates for a multiset use-case, and investigate the complexity of various aspects regarding multi-rule base inconsistency measurement.

Artificial intelligence has evolved from an esoteric research topic--with its origins six decades ago in corporate and academic computer science labs--into a collection of powerful technologies with mainstream business promise and applicability. Deloitte's global AI study finds that, in organizations adopting AI, more than eight in 10 leaders see AI as "very" or "critically" important to their business success in the next two years.1 AI adoption and spending are surging globally. According to one report, 37 percent of organizations have now deployed AI--a 270 percent increase from four years ago.2 Analysts project global spending on AI to top US$35 billion in 2019 and more than double to US$79.2 billion by 2022.3 What is driving this tremendous upswing? Many foresee AI helping to spur enormous productivity gains over the next decade, making it essential to the competitiveness of national economies.4

Background Based Conversations (BBCs) have been introduced to help conversational systems avoid generating overly generic responses. In a BBC the conversation is grounded in a knowledge source. A key challenge in BBCs is Knowledge Selection (KS): given a conversation context, try to find the appropriate background knowledge (a text fragment containing related facts or comments, etc.) based on which to generate the next response. Previous work addresses KS by employing attention and/or pointer mechanisms. These mechanisms use a local perspective, i.e., they select a token at a time based solely on the current decoding state. We argue for the adoption of a global perspective, i.e., pre-selecting some text fragments from the background knowledge that could help determine the topic of the next response. We enhance KS in BBCs by introducing a Global-to-Local Knowledge Selection (GLKS) mechanism. Given a conversation context and background knowledge, we first learn a topic transition vector to encode the most likely text fragments to be used in the next response, which is then used to guide the local KS at each decoding timestamp. In order to effectively learn the topic transition vector, we propose a distantly supervised learning schema. Experimental results show that the GLKS model significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations. More importantly, GLKS achieves this without requiring any extra annotations, which demonstrates its high scalability.

The rate of progress in the field of artificial intelligence is one of the most hotly contested aspects of the ongoing boom in teaching computers and robots how to see the world, make sense of it, and eventually perform complex tasks both in the physical realm and the virtual one. And just how fast the industry is moving, and to what end, is typically measured not just by actual product advancements and research milestones, but also by the prognostications and voiced concerns of AI leaders, futurists, academics, economists, and policymakers. AI is going to change the world -- but how and when are still open questions. Today, findings from a group of experts were published in an ongoing effort to help answer those questions. The experts include members of Harvard, MIT, Stanford, the nonprofit OpenAI, and the Partnership on AI industry consortium, among others, and they were put together as part of the second annual AI Index.

China has been the hottest story in robotics for the past year. With the Made in China 2025 plan, Xi Jinping's government literally came up with a roadmap for dominating the global robotics industry. An executive guide to the technology and market drivers behind the $135 billion robotics market. But is the hype warranted? Have recent trade tensions with the U.S. affected China's automation push?