DBOT can value any public traded company on the basis of Damodaran's analysis, and generates a report to support its position in an attempt to mimic its analytic parent. Until recently, such capabilities of analytic twins for financial valuation were not feasible. However, with advances in large language models (LLMs) and generative artificial intelligence (GenAI), it has become possible to conduct valuations that marry numbers and reasoning to generate credible valuations that can be used for long-term investing. The implications for automation and support of various parts of the valuation exercise are profound. In this paper, we provide a method for creating a digital analytic twin, DBOT, which is designed to mimic the investment analysis of individual companies by Damodaran. Since DBOT can value every company in an index such as the S&P500, it also provide an analysis in a macro sense, for example, by valuing the S&P500 market index relative to the valuation of its individual components. From the perspective of generative AI, DBOT presents a multitude of challenges. First and foremost, LLMs must be able to reason over financial texts, charts, tables, and spreadsheets. Furthermore, DBOT requires the AI system to follow Damodaran's

Extractive reading comprehension systems are designed to locate the correct answer to a question within a given text. However, a persistent challenge lies in ensuring these models maintain high accuracy in answering questions while reliably recognizing unanswerable queries. Despite significant advances in large language models (LLMs) for reading comprehension, this issue remains critical, particularly as the length of supported contexts continues to expand. To address this challenge, we propose an innovative data augmentation methodology grounded in a multi-agent collaborative framework. Unlike traditional methods, such as the costly human annotation process required for datasets like SQuAD 2.0, our method autonomously generates evidence-based question-answer pairs and systematically constructs unanswerable questions. Using this methodology, we developed the FactGuard-Bench dataset, which comprises 25,220 examples of both answerable and unanswerable question scenarios, with context lengths ranging from 8K to 128K. Experimental evaluations conducted on seven popular LLMs reveal that even the most advanced models achieve only 61.79% overall accuracy. Furthermore, we emphasize the importance of a model's ability to reason about unanswerable questions to avoid generating plausible but incorrect answers. By implementing efficient data selection and generation within the multi-agent collaborative framework, our method significantly reduces the traditionally high costs associated with manual annotation and provides valuable insights for the training and optimization of LLMs.

Multi-agent reinforcement learning (MARL) has shown promise for adaptive traffic signal control (ATSC), enabling multiple intersections to coordinate signal timings in real time. However, in large-scale settings, MARL faces constraints due to extensive data sharing and communication requirements. Federated learning (FL) mitigates these challenges by training shared models without directly exchanging raw data, yet traditional FL methods such as FedAvg struggle with highly heterogeneous intersections. Different intersections exhibit varying traffic patterns, demands, and road structures, so performing FedAvg across all agents is inefficient. To address this gap, we propose Hierarchical Federated Reinforcement Learning (HFRL) for ATSC. HFRL employs clustering-based or optimization-based techniques to dynamically group intersections and perform FedAvg independently within groups of intersections with similar characteristics, enabling more effective coordination and scalability than standard FedAvg. Our experiments on synthetic and real-world traffic networks demonstrate that HFRL not only outperforms both decentralized and standard federated RL approaches but also identifies suitable grouping patterns based on network structure or traffic demand, resulting in a more robust framework for distributed, heterogeneous systems.

Large Language Models (LLMs) have significantly advanced smart education in the Artificial General Intelligence (AGI) era. A promising application lies in the automatic generalization of instructional design for curriculum and learning activities, focusing on two key aspects: (1) Customized Generation: generating niche-targeted teaching content based on students' varying learning abilities and states, and (2) Intelligent Optimization: iteratively optimizing content based on feedback from learning effectiveness or test scores. Currently, a single large LLM cannot effectively manage the entire process, posing a challenge for designing intelligent teaching plans. To address these issues, we developed EduPlanner, an LLM-based multi-agent system comprising an evaluator agent, an optimizer agent, and a question analyst, working in adversarial collaboration to generate customized and intelligent instructional design for curriculum and learning activities. Taking mathematics lessons as our example, EduPlanner employs a novel Skill-Tree structure to accurately model the background mathematics knowledge of student groups, personalizing instructional design for curriculum and learning activities according to students' knowledge levels and learning abilities. Additionally, we introduce the CIDDP, an LLM-based five-dimensional evaluation module encompassing clarity, Integrity, Depth, Practicality, and Pertinence, to comprehensively assess mathematics lesson plan quality and bootstrap intelligent optimization. Experiments conducted on the GSM8K and Algebra datasets demonstrate that EduPlanner excels in evaluating and optimizing instructional design for curriculum and learning activities. Ablation studies further validate the significance and effectiveness of each component within the framework. Our code is publicly available at https://github.com/Zc0812/Edu_Planner

The concepts of convolutional neural networks (CNNs) and multi-agent systems are two important areas of research in artificial intelligence (AI). In this paper, we present an approach that builds a CNN-based colony of AI agents to serve as a single system and perform multiple tasks (e.g., predictions or classifications) in an environment. The proposed system impersonates the natural environment of a biological system, like an ant colony or a human colony. The proposed colony of AI that is defined as a role-based system uniquely contributes to accomplish tasks in an environment by incorporating AI agents that are fast learners, detailed learners, and organized learners. These learners can enhance their localized learning and their collective decisions as a single system of colony of AI agents. This approach also enhances the diversity and quality of the colony of AI with the help of Genetic Algorithms and their crossover and mutation mechanisms. The evolution of fast, detailed, and organized learners in the colony of AI is achieved by introducing a unique one-to-one mapping between these learners and the pretrained VGG16, VGG19, and ResNet50 models, respectively. This role-based approach creates two parent-AI agents using the AI models through the processes, called the intra- and inter-marriage of AI, so that they can share their learned knowledge (weights and biases) based on a probabilistic rule and produce diversified child-AI agents to perform new tasks. This process will form a colony of AI that consists of families of multi-model and mixture-model AI agents to improve diversity and quality. Simulations show that the colony of AI, built using the VGG16, VGG19, and ResNet50 models, can provide a single system that generates child-AI agents of excellent predictive performance, ranging between 82% and 95% of F1-scores, to make diversified collective and quality decisions on a task.

The use of AI in legal analysis and prediction (LegalAI) has gained widespread attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and underutilize the capabilities of modern large language models (LLMs). In this paper, inspired by the debate phase of real courtroom trials, we propose a novel legal judgment prediction model based on the Debate-Feedback architecture, which integrates LLM multi-agent debate and reliability evaluation models. Unlike traditional methods, our model achieves significant improvements in efficiency by minimizing the need for large historical datasets, thus offering a lightweight yet robust solution. Comparative experiments show that it outperforms several general-purpose and domain-specific legal models, offering a dynamic reasoning process and a promising direction for future LegalAI research.

This paper proposes a highly robust autonomous agent framework based on the ReAct paradigm, designed to solve complex tasks through adaptive decision making and multi-agent collaboration. Unlike traditional frameworks that rely on fixed workflows generated by LLM-based planners, this framework dynamically generates next actions during agent execution based on prior trajectories, thereby enhancing its robustness. To address potential termination issues caused by adaptive execution paths, I propose a timely abandonment strategy incorporating a probabilistic penalty mechanism. For multi-agent collaboration, I introduce a memory transfer mechanism that enables shared and dynamically updated memory among agents. The framework's innovative timely abandonment strategy dynamically adjusts the probability of task abandonment via probabilistic penalties, allowing developers to balance conservative and exploratory tendencies in agent execution strategies by tuning hyperparameters. This significantly improves adaptability and task execution efficiency in complex environments. Additionally, agents can be extended through external tool integration, supported by modular design and MCP protocol compatibility, which enables flexible action space expansion. Through explicit division of labor, the multi-agent collaboration mechanism enables agents to focus on specific task components, thereby significantly improving execution efficiency and quality.

Our main contribution is the introduction of the map of elections framework. A map of elections consists of three main elements: (1) a dataset of elections (i.e., collections of ordinal votes over given sets of candidates), (2) a way of measuring similarities between these elections, and (3) a representation of the elections in the 2D Euclidean space as points, so that the more similar two elections are, the closer are their points. In our maps, we mostly focus on datasets of synthetic elections, but we also show an example of a map over real-life ones. To measure similarities, we would have preferred to use, e.g., the isomorphic swap distance, but this is infeasible due to its high computational complexity. Hence, we propose polynomial-time computable positionwise distance and use it instead. Regarding the representations in 2D Euclidean space, we mostly use the Kamada-Kawai algorithm, but we also show two alternatives. We develop the necessary theoretical results to form our maps and argue experimentally that they are accurate and credible. Further, we show how coloring the elections in a map according to various criteria helps in analyzing results of a number of experiments. In particular, we show colorings according to the scores of winning candidates or committees, running times of ILP-based winner determination algorithms, and approximation ratios achieved by particular algorithms.

Over the past three decades, Hicks has watched the Pentagon transform--politically, strategically, and technologically. She entered government in the 1990s at the tail end of the Cold War, when optimism and a belief in global cooperation still dominated US foreign policy. After 9/11, the focus shifted to counterterrorism and nonstate actors. Then came Russia's resurgence and China's growing assertiveness. Hicks took two previous breaks from government work--the first to complete a PhD at MIT and joining the think thank Center for Strategic and International Studies (CSIS), which she later rejoined to lead its International Security Program after her second tour. "By the time I returned in 2021," she says, "there was one actor--the PRC (People's Republic of China)--that had the capability and the will to really contest the international system as it's set up."

This paper introduces a multi-agent application system designed to enhance office collaboration efficiency and work quality. The system integrates artificial intelligence, machine learning, and natural language processing technologies, achieving functionalities such as task allocation, progress monitoring, and information sharing. The agents within the system are capable of providing personalized collaboration support based on team members' needs and incorporate data analysis tools to improve decision-making quality. The paper also proposes an intelligent agent architecture that separates Plan and Solver, and through techniques such as multi-turn query rewriting and business tool retrieval, it enhances the agent's multi-intent and multi-turn dialogue capabilities. Furthermore, the paper details the design of tools and multi-turn dialogue in the context of office collaboration scenarios, and validates the system's effectiveness through experiments and evaluations. Ultimately, the system has demonstrated outstanding performance in real business applications, particularly in query understanding, task planning, and tool calling. Looking forward, the system is expected to play a more significant role in addressing complex interaction issues within dynamic environments and large-scale multi-agent systems.